Andrew Gordon Wilson

ICLR Conference 2025 Conference Paper

Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences

• Alan Nawzad Amin
• Nate Gruver
• Yilun Kuang
• Yucen Lily Li
• Hunter Elliott
• Calvin McCarter
• Aniruddh Raghu
• Peyton Greenside

To build effective therapeutics, biologists iteratively mutate antibody sequences to improve binding and stability. Proposed mutations can be informed by previous measurements or by learning from large antibody databases to predict only typical antibodies. Unfortunately, the space of typical antibodies is enormous to search, and experiments often fail to find suitable antibodies on a budget. We introduce Clone-informed Bayesian Optimization (CloneBO), a Bayesian optimization procedure that efficiently optimizes antibodies in the lab by teaching a generative model how our immune system optimizes antibodies. Our immune system makes antibodies by iteratively evolving specific portions of their sequences to bind their target strongly and stably, resulting in a set of related, evolving sequences known as a *clonal family*. We train a large language model, CloneLM, on hundreds of thousands of clonal families and use it to design sequences with mutations that are most likely to optimize an antibody within the human immune system. We propose to guide our designs to fit previous measurements with a twisted sequential Monte Carlo procedure. We show that CloneBO optimizes antibodies substantially more efficiently than previous methods in realistic *in silico* experiments and designs stronger and more stable binders in *in vitro* wet lab experiments.

ICLR Conference 2025 Conference Paper

Compute-Optimal LLMs Provably Generalize Better with Scale

• Marc Anton Finzi
• Sanyam Kapoor
• Diego Granziol
• Anming Gu
• Christopher De Sa
• J. Zico Kolter
• Andrew Gordon Wilson

Why do larger language models generalize better? To explore this question, we develop generalization bounds on the pretraining objective of large language models (LLMs) in the compute-optimal regime, as described by the Chinchilla scaling laws. We introduce a novel, fully empirical Freedman-type martingale concentration inequality that tightens existing bounds by accounting for the variance of the loss function. The generalization bound can be broken into three contributions: the number of parameters per token, the loss variance, and the quantization error at a fixed bitrate. As language models are scaled up, the number of parameters per data point stays constant; however, both the loss variance and the quantization error decrease, implying that larger models should have \emph{smaller} generalization gaps. We examine why larger models tend to be more quantizable from an information theoretic perspective, showing that the rate at which they can integrate new information grows slower than their capacity on the compute optimal frontier. From these findings we produce a scaling law for the generalization gap, showing that our bounds decrease in a predictable way.

ICML Conference 2025 Conference Paper

Customizing the Inductive Biases of Softmax Attention using Structured Matrices

• Yilun Kuang
• Noah Amsel
• Sanae Lotfi
• Shikai Qiu
• Andres Potapczynski
• Andrew Gordon Wilson

The core component of attention is the scoring function, which transforms the inputs into low-dimensional queries and keys and takes the dot product of each pair. While the low-dimensional projection improves efficiency, it causes information loss for certain tasks that have intrinsically high-dimensional inputs. Additionally, attention uses the same scoring function for all input pairs, without imposing a distance-dependent compute bias for neighboring tokens in the sequence. In this work, we address these shortcomings by proposing new scoring functions based on computationally efficient structured matrices with high ranks, including Block Tensor-Train (BTT) and Multi-Level Low Rank (MLR) matrices. On in-context regression tasks with high-dimensional inputs, our proposed scoring functions outperform standard attention for any fixed compute budget. On language modeling, a task that exhibits locality patterns, our MLR-based attention method achieves improved scaling laws compared to both standard attention and variants of sliding window attention. Additionally, we show that both BTT and MLR fall under a broader family of efficient structured matrices capable of encoding either full-rank or distance-dependent compute biases, thereby addressing significant shortcomings of standard attention.

ICML Conference 2025 Conference Paper

Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization

• Luca Masserano
• Abdul Fatir Ansari
• Boran Han
• Xiyuan Zhang
• Christos Faloutsos
• Michael W. Mahoney
• Andrew Gordon Wilson
• Youngsuk Park

How to best develop foundational models for time series forecasting remains an important open question. Tokenization is a crucial consideration in this effort: what is an effective discrete vocabulary for a real-valued sequential input? To address this question, we develop WaveToken, a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies. Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon. By decomposing coarse and fine structures in the inputs, wavelets provide an eloquent and compact language for time series forecasting that simplifies learning. Empirical results on a comprehensive benchmark, including 42 datasets for both in-domain and zero-shot settings, show that WaveToken: i) performs on par or better than recently proposed foundation models for forecasting while using a much smaller vocabulary (1024 tokens), and is competitive with modern deep learning models trained specifically on each dataset; ii) exhibits superior generalization capabilities, achieving the best average rank across all datasets for three complementary metrics; and iii) easily captures complex temporal patterns of practical relevance that are challenging for other recent pre-trained models, including trends, sparse spikes, and non-stationary time series with varying frequencies evolving over time.

TMLR Journal 2025 Journal Article

Reliable and Responsible Foundation Models

• Xinyu Yang
• Junlin Han
• Rishi Bommasani
• Jinqi Luo
• Wenjie Qu
• Wangchunshu Zhou
• Adel Bibi
• Xiyao Wang

Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with broad applications across various domains such as law, medicine, education, finance, and beyond. As these models see increasing real-world deployment, ensuring their reliability and responsibility has become critical for academia, industry, and government. This survey addresses the reliable and responsible development of foundation models. We explore critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift. Our research also covers model limitations, such as hallucinations, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection. For each area, we review the current state of the field and outline concrete future research directions. Additionally, we discuss the intersections between these areas, highlighting their connections and shared challenges. We hope our survey fosters the development of foundation models that are not only powerful but also ethical, trustworthy, reliable, and socially responsible.

ICML Conference 2025 Conference Paper

Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks

• Shikai Qiu
• Lechao Xiao
• Andrew Gordon Wilson
• Jeffrey Pennington
• Atish Agarwala

What scaling limits govern neural network training dynamics when model size and training time grow in tandem? We show that despite the complex interactions between architecture, training algorithms, and data, compute-optimally trained models exhibit a remarkably precise universality. Specifically, loss curves from models of varying sizes collapse onto a single universal curve when training compute and loss are normalized to unity at the end of training. With learning rate decay, the collapse becomes so tight that differences in the normalized curves across models fall below the noise floor of individual loss curves across random seeds, a phenomenon we term supercollapse. We observe supercollapse across learning rate schedules, datasets, and architectures, including transformers trained on next-token prediction, and find it breaks down when hyperparameters are scaled suboptimally, providing a precise and practical indicator of good scaling. We explain these phenomena by connecting collapse to the power-law structure in typical neural scaling laws, and analyzing a simple yet surprisingly effective model of SGD noise dynamics that accurately predicts loss curves across various learning rate schedules and quantitatively explains the origin of supercollapse.

ICML Conference 2025 Conference Paper

Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra

• Alan Nawzad Amin
• Andres Potapczynski
• Andrew Gordon Wilson

To understand how genetic variants in human genomes manifest in phenotypes - traits like height or diseases like asthma - geneticists have sequenced and measured hundreds of thousands of individuals. Geneticists use this data to build models that predict how a genetic variant impacts phenotype given genomic features of the variant, like DNA accessibility or the presence of nearby DNA-bound proteins. As more data and features become available, one might expect predictive models to improve. Unfortunately, training these models is bottlenecked by the need to solve expensive linear algebra problems because variants in the genome are correlated with nearby variants, requiring inversion of large matrices. Previous methods have therefore been restricted to fitting small models, and fitting simplified summary statistics, rather than the full likelihood of the statistical model. In this paper, we leverage modern fast linear algebra techniques to develop DeepWAS (Deep genome Wide Association Studies), a method to train large and flexible neural network predictive models to optimize likelihood. Surprisingly, we find that larger models only improve performance when using our full likelihood approach; when trained by fitting traditional summary statistics, larger models perform no better than small ones. We find larger models trained on more features make better predictions, potentially improving disease predictions and therapeutic target identification.

ICLR Conference 2024 Conference Paper

A Study of Bayesian Neural Network Surrogates for Bayesian Optimization

• Yucen Lily Li
• Tim G. J. Rudner
• Andrew Gordon Wilson

Bayesian optimization is a highly efficient approach to optimizing objective functions which are expensive to query. These objectives are typically represented by Gaussian process (GP) surrogate models which are easy to optimize and support exact inference. While standard GP surrogates have been well-established in Bayesian optimization, Bayesian neural networks (BNNs) have recently become practical function approximators, with many benefits over standard GPs such as the ability to naturally handle non-stationarity and learn representations for high-dimensional data. In this paper, we study BNNs as alternatives to standard GP surrogates for optimization. We consider a variety of approximate inference procedures for finite-width BNNs, including high-quality Hamiltonian Monte Carlo, low-cost stochastic MCMC, and heuristics such as deep ensembles. We also consider infinite-width BNNs, linearized Laplace approximations, and partially stochastic models such as deep kernel learning. We evaluate this collection of surrogate models on diverse problems with varying dimensionality, number of objectives, non-stationarity, and discrete and continuous inputs. We find: (i) the ranking of methods is highly problem dependent, suggesting the need for tailored inductive biases; (ii) HMC is the most successful approximate inference procedure for fully stochastic BNNs; (iii) full stochasticity may be unnecessary as deep kernel learning is relatively competitive; (iv) deep ensembles perform relatively poorly; (v) infinite-width BNNs are particularly promising, especially in high dimensions.

TMLR Journal 2024 Journal Article

Chronos: Learning the Language of Time Series

• Abdul Fatir Ansari
• Lorenzo Stella
• Ali Caner Turkmen
• Xiyuan Zhang
• Pedro Mercado
• Huibin Shen
• Oleksandr Shchur
• Syama Sundar Rangapuram

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based language model architectures on these tokenized time series via the cross-entropy loss. We pretrained Chronos models based on the T5 family (ranging from 20M to 710M parameters) on a large collection of publicly available datasets, complemented by a synthetic dataset that we generated via Gaussian processes to improve generalization. In a comprehensive benchmark consisting of 42 datasets, and comprising both classical local models and deep learning methods, we show that Chronos models: (a) significantly outperform other methods on datasets that were part of the training corpus; and (b) have comparable and occasionally superior zero-shot performance on new datasets, relative to methods that were trained specifically on them. Our results demonstrate that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks, positioning pretrained models as a viable tool to greatly simplify forecasting pipelines.

ICML Conference 2024 Conference Paper

Compute Better Spent: Replacing Dense Layers with Structured Matrices

• Shikai Qiu
• Andres Potapczynski
• Marc Anton Finzi
• Micah Goldblum
• Andrew Gordon Wilson

Dense linear layers are the dominant computational bottleneck in foundation models. Identifying more efficient alternatives to dense matrices has enormous potential for building more compute-efficient models, as exemplified by the success of convolutional networks in the image domain. In this work, we systematically explore structured matrices as replacements for dense matrices. We show that different structures often require drastically different initialization scales and learning rates, which are crucial to performance, especially as models scale. Using insights from the Maximal Update Parameterization, we determine the optimal scaling for initialization and learning rates of these unconventional layers. Finally, we measure the scaling laws of different structures to compare how quickly their performance improves with compute. We propose a novel matrix family containing Monarch matrices, the Block Tensor-Train (BTT), which we show performs better than dense matrices for the same compute on multiple tasks. On CIFAR-10/100 with augmentation, BTT achieves exponentially lower training loss than dense when training MLPs and ViTs. BTT matches dense ViT-S/32 performance on ImageNet-1k with 3. 8 times less compute and is more efficient than dense for training small GPT-2 language models.

ICML Conference 2024 Conference Paper

Controllable Prompt Tuning For Balancing Group Distributional Robustness

• Hoang Phan
• Andrew Gordon Wilson
• Qi Lei

Models trained on data composed of different groups or domains can suffer from severe performance degradation under distribution shifts. While recent methods have largely focused on optimizing the worst-group objective, this often comes at the expense of good performance on other groups. To address this problem, we introduce an optimization scheme to achieve good performance across groups and find a good solution for all without severely sacrificing performance on any of them. However, directly applying such optimization involves updating the parameters of the entire network, making it both computationally expensive and challenging. Thus, we introduce Controllable Prompt Tuning (CPT), which couples our approach with prompt-tuning techniques. On spurious correlation benchmarks, our procedures achieve state-of-the-art results across both transformer and non-transformer architectures, as well as unimodal and multimodal data, while requiring only $0. 4%$ tunable parameters.

ICLR Conference 2024 Conference Paper

Fine-Tuned Language Models Generate Stable Inorganic Materials as Text

• Nate Gruver
• Anuroop Sriram
• Andrea Madotto
• Andrew Gordon Wilson
• C. Lawrence Zitnick
• Zachary W. Ulissi

We propose fine-tuning large language models for generation of stable materials. While unorthodox, fine-tuning large language models on text-encoded atomistic data is simple to implement yet reliable, with around 90\% of sampled structures obeying physical constraints on atom positions and charges. Using energy above hull calculations from both learned ML potentials and gold-standard DFT calculations, we show that our strongest model (fine-tuned LLaMA-2 70B) can generate materials predicted to be metastable at about twice the rate (49\% vs 28\%) of CDVAE, a competing diffusion model. Because of text prompting's inherent flexibility, our models can simultaneously be used for unconditional generation of stable material, infilling of partial structures and text-conditional generation. Finally, we show that language models' ability to capture key symmetries of crystal structures improves with model scale, suggesting that the biases of pretrained LLMs are surprisingly well-suited for atomistic data.

JMLR Journal 2024 Journal Article

Fortuna: A Library for Uncertainty Quantification in Deep Learning

• Gianluca Detommaso
• Alberto Gasparin
• Michele Donini
• Matthias Seeger
• Andrew Gordon Wilson
• Cedric Archambeau

We present Fortuna, an open-source library for uncertainty quantification in deep learning. Fortuna supports a range of calibration techniques, such as conformal prediction that can be applied to any trained neural network to generate reliable uncertainty estimates, and scalable Bayesian inference methods that can be applied to deep neural networks trained from scratch for improved uncertainty quantification and accuracy. By providing a coherent framework for advanced uncertainty quantification methods, Fortuna simplifies the process of benchmarking and helps practitioners build robust AI systems. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2024. ( edit, beta )

ICML Conference 2024 Conference Paper

Modeling Caption Diversity in Contrastive Vision-Language Pretraining

• Samuel Lavoie
• Polina Kirichenko
• Mark Ibrahim
• Mahmoud Assran
• Andrew Gordon Wilson
• Aaron C. Courville
• Nicolas Ballas

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector – limiting how well CLIP-like models can represent the diverse ways to describe an image. In this work, we introduce Llip, Latent Language Image Pretraining, which models the diversity of captions that could match an image. Llip’s vision encoder outputs a set of visual features that are mixed into a final representation by conditioning on information derived from the text. We show that Llip outperforms non-contextualized baselines like CLIP and SigLIP on a variety of tasks even with large-scale encoders. Llip improves zero-shot classification by an average of 2. 9% zero-shot classification benchmarks with a ViT-G/14 encoder. Specifically, Llip attains a zero-shot top-1 accuracy of 83. 5% on ImageNet outperforming a similarly sized CLIP by 1. 4%. We also demonstrate improvement on zero-shot retrieval on MS-COCO by 6. 0%. We provide a comprehensive analysis of the components introduced by the method and demonstrate that Llip leads to richer visual representations.

ICML Conference 2024 Conference Paper

Non-Vacuous Generalization Bounds for Large Language Models

• Sanae Lotfi
• Marc Anton Finzi
• Yilun Kuang
• Tim G. J. Rudner
• Micah Goldblum
• Andrew Gordon Wilson

Modern language models can contain billions of parameters, raising the question of whether they can generalize beyond the training data or simply parrot their training corpora. We provide the first non-vacuous generalization bounds for pretrained large language models (LLMs), indicating that language models are capable of discovering regularities that generalize to unseen data. In particular, we derive a compression bound that is valid for the unbounded log-likelihood loss using prediction smoothing, and we extend the bound to handle subsampling, making bound computation 900 times faster on massive datasets. To achieve the extreme level of compression required for non-vacuous bounds, we devise SubLoRA, a simple low-dimensional nonlinear parameterization that leads to non-vacuous generalization bounds for very large models with up to 849 million parameters. Finally, we use our bounds to understand LLM generalization and find that larger models have better generalization bounds and are more compressible than smaller models.

ICML Conference 2024 Conference Paper

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

• Theodore Papamarkou
• Maria Skoularidou
• Konstantina Palla
• Laurence Aitchison
• Julyan Arbel
• David B. Dunson
• Maurizio Filippone
• Vincent Fortuin

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.

ICML Conference 2024 Conference Paper

Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

• Micah Goldblum
• Marc Anton Finzi
• Keefer Rowan
• Andrew Gordon Wilson

No free lunch theorems for supervised learning state that no learner can solve all problems or that all learners achieve exactly the same accuracy on average over a uniform distribution on learning problems. Accordingly, these theorems are often referenced in support of the notion that individual problems require specially tailored inductive biases. While virtually all uniformly sampled datasets have high complexity, real-world problems disproportionately generate low-complexity data, and we argue that neural network models share this same preference, formalized using Kolmogorov complexity. Notably, we show that architectures designed for a particular domain, such as computer vision, can compress datasets on a variety of seemingly unrelated domains. Our experiments show that pre-trained and even randomly initialized language models prefer to generate low-complexity sequences. Whereas no free lunch theorems seemingly indicate that individual problems require specialized learners, we explain how tasks that often require human intervention such as picking an appropriately sized model when labeled data is scarce or plentiful can be automated into a single learning algorithm. These observations justify the trend in deep learning of unifying seemingly disparate problems with an increasingly small set of machine learning models.

ICML Conference 2024 Conference Paper

Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency

• Alan Nawzad Amin
• Andrew Gordon Wilson

To make accurate predictions, understand mechanisms, and design interventions in systems of many variables, we wish to learn causal graphs from large scale data. Unfortunately the space of all possible causal graphs is enormous so scalably and accurately searching for the best fit to the data is a challenge. In principle we could substantially decrease the search space, or learn the graph entirely, by testing the conditional independence of variables. However, deciding if two variables are adjacent in a causal graph may require an exponential number of tests. Here we build a scalable and flexible method to evaluate if two variables are adjacent in a causal graph, the Differentiable Adjacency Test (DAT). DAT replaces an exponential number of tests with a provably equivalent relaxed problem. It then solves this problem by training two neural networks. We build a graph learning method based on DAT, DAT-Graph, that can also learn from data with interventions. DAT-Graph can learn graphs of 1000 variables with state of the art accuracy. Using the graph learned by DAT-Graph, we also build models that make much more accurate predictions of the effects of interventions on large scale RNA sequencing data.

ICML Conference 2024 Conference Paper

Transferring Knowledge From Large Foundation Models to Small Downstream Models

• Shikai Qiu
• Boran Han
• Danielle C. Maddix
• Shuai Zhang 0007
• Yuyang Wang 0001
• Andrew Gordon Wilson

How do we transfer the relevant knowledge from ever larger foundation models into small, task-specific downstream models that can run at much lower costs? Standard transfer learning using pre-trained weights as the initialization transfers limited information and commits us to often massive pre-trained architectures. This procedure also precludes combining multiple pre-trained models that learn complementary information. To address these shortcomings, we introduce Adaptive Feature Transfer (AFT). Instead of transferring weights, AFT operates purely on features, thereby decoupling the choice of the pre-trained model from the smaller downstream model. Rather than indiscriminately compressing all pre-trained features, AFT adaptively transfers pre-trained features that are most useful for performing the downstream task, using a simple regularization that adds minimal overhead. Across multiple vision, language, and multi-modal datasets, AFT achieves significantly better downstream performance compared to alternatives with a similar computational cost. Furthermore, AFT reliably translates improvement in pre-trained models into improvement in downstream performance, even if the downstream model is over $50\times$ smaller, and can effectively transfer complementary information learned by multiple pre-trained models.

ICLR Conference 2023 Conference Paper

A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks

• Marc Anton Finzi
• Andres Potapczynski
• Matthew Choptuik
• Andrew Gordon Wilson

Unlike conventional grid and mesh based methods for solving partial differential equations (PDEs), neural networks have the potential to break the curse of dimensionality, providing approximate solutions to problems where using classical solvers is difficult or impossible. While global minimization of the PDE residual over the network parameters works well for boundary value problems, catastrophic forgetting impairs applicability to initial value problems (IVPs). In an alternative local-in-time approach, the optimization problem can be converted into an ordinary differential equation (ODE) on the network parameters and the solution propagated forward in time; however, we demonstrate that current methods based on this approach suffer from two key issues. First, following the ODE produces an uncontrolled growth in the conditioning of the problem, ultimately leading to unacceptably large numerical errors. Second, as the ODE methods scale cubically with the number of model parameters, they are restricted to small neural networks, significantly limiting their ability to represent intricate PDE initial conditions and solutions. Building on these insights, we develop Neural-IVP, an ODE based IVP solver which prevents the network from getting ill-conditioned and runs in time linear in the number of parameters, enabling us to evolve the dynamics of challenging PDEs with neural networks.

ICML Conference 2023 Conference Paper

Function-Space Regularization in Neural Networks: A Probabilistic Perspective

• Tim G. J. Rudner
• Sanyam Kapoor
• Shikai Qiu
• Andrew Gordon Wilson

Parameter-space regularization in neural network optimization is a fundamental tool for improving generalization. However, standard parameter-space regularization methods make it challenging to encode explicit preferences about desired predictive functions into neural network training. In this work, we approach regularization in neural networks from a probabilistic perspective and show that by viewing parameter-space regularization as specifying an empirical prior distribution over the model parameters, we can derive a probabilistically well-motivated regularization technique that allows explicitly encoding information about desired predictive functions into neural network training. This method—which we refer to as function-space empirical Bayes (FS-EB)—includes both parameter- and function-space regularization, is mathematically simple, easy to implement, and incurs only minimal computational overhead compared to standard regularization techniques. We evaluate the utility of this regularization technique empirically and demonstrate that the proposed method leads to near-perfect semantic shift detection, highly-calibrated predictive uncertainty estimates, successful task adaption from pre-trained models, and improved generalization under covariate shift.

ICLR Conference 2023 Conference Paper

How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization

• Jonas Geiping
• Micah Goldblum
• Gowthami Somepalli
• Ravid Shwartz-Ziv
• Tom Goldstein
• Andrew Gordon Wilson

Despite the clear performance benefits of data augmentations, little is known about why they are so effective. In this paper, we disentangle several key mechanisms through which data augmentations operate. Establishing an exchange rate between augmented and additional real data, we find that in out-of-distribution testing scenarios, augmentations which yield samples that are diverse, but inconsistent with the data distribution can be even more valuable than additional training data. Moreover, we find that data augmentations which encourage invariances can be more valuable than invariance alone, especially on small and medium sized training sets. Following this observation, we show that augmentations induce additional stochasticity during training, effectively flattening the loss landscape.

ICLR Conference 2023 Conference Paper

Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations

• Polina Kirichenko
• Pavel Izmailov
• Andrew Gordon Wilson

Neural network classifiers can largely rely on simple spurious features, such as image backgrounds, to make predictions. However, even in these cases, we show that they still often learn core features associated with the desired attributes of the data, contrary to recent findings. Inspired by this insight, we demonstrate that simple last layer retraining can match or outperform state-of-the-art approaches on spurious correlation benchmarks, but with profoundly lower complexity and computational expenses. Moreover, we show that last layer retraining on large ImageNet-trained models can also significantly reduce reliance on background and texture information, improving robustness to covariate shift, after only minutes of training on a single GPU.

ICLR Conference 2023 Conference Paper

Learning Multimodal Data Augmentation in Feature Space

• Zichang Liu
• Zhiqiang Tang 0001
• Xingjian Shi
• Aston Zhang
• Mu Li 0003
• Anshumali Shrivastava
• Andrew Gordon Wilson

The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances in designing neural networks to harness multimodal data, the enormous success of data augmentation currently remains limited to single-modality tasks like image classification. Indeed, it is particularly difficult to augment each modality while preserving the overall semantic structure of the data; for example, a caption may no longer be a good description of an image after standard augmentations have been applied, such as translation. Moreover, it is challenging to specify reasonable transformations that are not tailored to a particular modality. In this paper, we introduce LeMDA, Learning Multimodal Data Augmentation, an easy-to-use method that automatically learns to jointly augment multimodal data in feature space, with no constraints on the identities of the modalities or the relationship between modalities. We show that LeMDA can (1) profoundly improve the performance of multimodal deep learning architectures, (2) apply to combinations of modalities that have not been previously considered, and (3) achieve state-of-the-art results on a wide range of applications comprised of image, text, and tabular data.

ICML Conference 2023 Conference Paper

Simple and Fast Group Robustness by Automatic Feature Reweighting

• Shikai Qiu
• Andres Potapczynski
• Pavel Izmailov
• Andrew Gordon Wilson

A major challenge to out-of-distribution generalization is reliance on spurious features — patterns that are predictive of the class label in the training data distribution, but not causally related to the target. Standard methods for reducing the reliance on spurious features typically assume that we know what the spurious feature is, which is rarely true in the real world. Methods that attempt to alleviate this limitation are complex, hard to tune, and lead to a significant computational overhead compared to standard training. In this paper, we propose Automatic Feature Reweighting (AFR), an extremely simple and fast method for updating the model to reduce the reliance on spurious features. AFR retrains the last layer of a standard ERM-trained base model with a weighted loss that emphasizes the examples where the ERM model predicts poorly, automatically upweighting the minority group without group labels. With this simple procedure, we improve upon the best reported results among competing methods trained without spurious attributes on several vision and natural language classification benchmarks, using only a fraction of their compute.

ICLR Conference 2023 Conference Paper

The Lie Derivative for Measuring Learned Equivariance

• Nate Gruver
• Marc Anton Finzi
• Micah Goldblum
• Andrew Gordon Wilson

Equivariance guarantees that a model's predictions capture key symmetries in data. When an image is translated or rotated, an equivariant model's representation of that image will translate or rotate accordingly. The success of convolutional neural networks has historically been tied to translation equivariance directly encoded in their architecture. The rising success of vision transformers, which have no explicit architectural bias towards equivariance, challenges this narrative and suggests that augmentations and training data might also play a significant role in their performance. In order to better understand the role of equivariance in recent vision models, we apply the Lie derivative, a method for measuring equivariance with strong mathematical foundations and minimal hyperparameters. Using the Lie derivative, we study the equivariance properties of hundreds of pretrained models, spanning CNNs, transformers, and Mixer architectures. The scale of our analysis allows us to separate the impact of architecture from other factors like model size or training method. Surprisingly, we find that many violations of equivariance can be linked to spatial aliasing in ubiquitous network layers, such as pointwise non-linearities, and that as models get larger and more accurate they tend to display more equivariance, regardless of architecture. For example, transformers can be more equivariant than convolutional neural networks after training.

ICLR Conference 2023 Conference Paper

Transfer Learning with Deep Tabular Models

• Roman Levin
• Valeriia Cherepanova
• Avi Schwarzschild
• Arpit Bansal
• C. Bayan Bruss
• Tom Goldstein
• Andrew Gordon Wilson
• Micah Goldblum

Recent work on deep learning for tabular data demonstrates the strong performance of deep tabular models, often bridging the gap between gradient boosted decision trees and neural networks. Accuracy aside, a major advantage of neural models is that they are easily fine-tuned in new domains and learn reusable features. This property is often exploited in computer vision and natural language applications, where transfer learning is indispensable when task-specific training data is scarce. In this work, we explore the benefits that representation learning provides for knowledge transfer in the tabular domain. We conduct experiments in a realistic medical diagnosis test bed with limited amounts of downstream data and find that transfer learning with deep tabular models provides a definitive advantage over gradient boosted decision tree methods. We further compare the supervised and self-supervised pretraining strategies and provide practical advice on transfer learning with tabular models. Finally, we propose a pseudo-feature method for cases where the upstream and downstream feature sets differ, a tabular-specific problem widespread in real-world applications.

ICML Conference 2023 Conference Paper

User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems

• Marc Anton Finzi
• Anudhyan Boral
• Andrew Gordon Wilson
• Fei Sha
• Leonardo Zepeda-Núñez

Diffusion models are a class of probabilistic generative models that have been widely used as a prior for image processing tasks like text conditional generation and inpainting. We demonstrate that these models can be adapted to make predictions and provide uncertainty quantification for chaotic dynamical systems. In these applications, diffusion models can implicitly represent knowledge about outliers and extreme events; however, querying that knowledge through conditional sampling or measuring probabilities is surprisingly difficult. Existing methods for conditional sampling at inference time seek mainly to enforce the constraints, which is insufficient to match the statistics of the distribution or compute the probability of the chosen events. To achieve these ends, optimally one would use the conditional score function, but its computation is typically intractable. In this work, we develop a probabilistic approximation scheme for the conditional score function which provably converges to the true distribution as the noise level decreases. With this scheme we are able to sample conditionally on nonlinear user-defined events at inference time, and matches data statistics even when sampling from the tails of the distribution.

ICML Conference 2022 Conference Paper

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

• Samuel Don Stanton
• Wesley J. Maddox
• Nate Gruver
• Phillip M. Maffettone
• Emily Delaney
• Peyton Greenside
• Andrew Gordon Wilson

Bayesian optimization (BayesOpt) is a gold standard for query-efficient continuous optimization. However, its adoption for drug design has been hindered by the discrete, high-dimensional nature of the decision variables. We develop a new approach (LaMBO) which jointly trains a denoising autoencoder with a discriminative multi-task Gaussian process head, allowing gradient-based optimization of multi-objective acquisition functions in the latent space of the autoencoder. These acquisition functions allow LaMBO to balance the explore-exploit tradeoff over multiple design rounds, and to balance objective tradeoffs by optimizing sequences at many different points on the Pareto frontier. We evaluate LaMBO on two small-molecule design tasks, and introduce new tasks optimizing in silico and in vitro properties of large-molecule fluorescent proteins. In our experiments LaMBO outperforms genetic optimizers and does not require a large pretraining corpus, demonstrating that BayesOpt is practical and effective for biological sequence design.

ICML Conference 2022 Conference Paper

Bayesian Model Selection, the Marginal Likelihood, and Generalization

• Sanae Lotfi
• Pavel Izmailov
• Gregory W. Benton
• Micah Goldblum
• Andrew Gordon Wilson

How do we compare between hypotheses that are entirely consistent with observations? The marginal likelihood (aka Bayesian evidence), which represents the probability of generating our observations from a prior, provides a distinctive approach to this foundational question, automatically encoding Occam’s razor. Although it has been observed that the marginal likelihood can overfit and is sensitive to prior assumptions, its limitations for hyperparameter learning and discrete model comparison have not been thoroughly investigated. We first revisit the appealing properties of the marginal likelihood for learning constraints and hypothesis testing. We then highlight the conceptual and practical issues in using the marginal likelihood as a proxy for generalization. Namely, we show how marginal likelihood can be negatively correlated with generalization, with implications for neural architecture search, and can lead to both underfitting and overfitting in hyperparameter learning. We provide a partial remedy through a conditional marginal likelihood, which we show is more aligned with generalization, and practically valuable for large-scale hyperparameter learning, such as in deep kernel learning.

ICLR Conference 2022 Conference Paper

Deconstructing the Inductive Biases of Hamiltonian Neural Networks

• Nate Gruver
• Marc Anton Finzi
• Samuel Don Stanton
• Andrew Gordon Wilson

Physics-inspired neural networks (NNs), such as Hamiltonian or Lagrangian NNs, dramatically outperform other learned dynamics models by leveraging strong inductive biases. These models, however, are challenging to apply to many real world systems, such as those that don’t conserve energy or contain contacts, a common setting for robotics and reinforcement learning. In this paper, we examine the inductive biases that make physics-inspired models successful in practice. We show that, contrary to conventional wisdom, the improved generalization of HNNs is the result of modeling acceleration directly and avoiding artificial complexity from the coordinate system, rather than symplectic structure or energy conservation. We show that by relaxing the inductive biases of these models, we can match or exceed performance on energy-conserving systems while dramatically improving performance on practical, non-conservative systems. We extend this approach to constructing transition models for common Mujoco environments, showing that our model can appropriately balance inductive biases with the flexibility required for model-based control.

UAI Conference 2022 Conference Paper

Low-precision arithmetic for fast Gaussian processes

• Wesley J. Maddox
• Andres Potapczynski
• Andrew Gordon Wilson

Low precision arithmetic has had a transformative effect on the training of neural networks, reducing computation, memory and energy requirements. However, despite their promise, low precision operations have received little attention for Gaussian process (GP) training, largely because GPs require sophisticated linear algebra routines that are unstable in low precision. We study the different failure modes that can occur when training GPs in half-precision. To circumvent these failure modes, we propose a multi-faceted approach involving conjugate gradients with re-orthogonalization, mixed precision, compact kernels, and preconditioners. Our approach significantly improves the numerical stability and practical performance of conjugate gradients in low precision over a wide range of settings, and reduces the runtime of 1. 8 million data points to 10 hours on a single GPU, without requiring any sparse approximations.

ICML Conference 2022 Conference Paper

Low-Precision Stochastic Gradient Langevin Dynamics

• Ruqi Zhang
• Andrew Gordon Wilson
• Christopher De Sa

While low-precision optimization has been widely used to accelerate deep learning, low-precision sampling remains largely unexplored. As a consequence, sampling is simply infeasible in many large-scale scenarios, despite providing remarkable benefits to generalization and uncertainty estimation for neural networks. In this paper, we provide the first study of low-precision Stochastic Gradient Langevin Dynamics (SGLD), showing that its costs can be significantly reduced without sacrificing performance, due to its intrinsic ability to handle system noise. We prove that the convergence of low-precision SGLD with full-precision gradient accumulators is less affected by the quantization error than its SGD counterpart in the strongly convex setting. To further enable low-precision gradient accumulators, we develop a new quantization function for SGLD that preserves the variance in each update step. We demonstrate that low-precision SGLD achieves comparable performance to full-precision SGLD with only 8 bits on a variety of deep learning tasks.

ICML Conference 2022 Conference Paper

Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes

• Gregory W. Benton
• Wesley J. Maddox
• Andrew Gordon Wilson

A broad class of stochastic volatility models are defined by systems of stochastic differential equations, and while these models have seen widespread success in domains such as finance and statistical climatology, they typically lack an ability to condition on historical data to produce a true posterior distribution. To address this fundamental limitation, we show how to re-cast a class of stochastic volatility models as a hierarchical Gaussian process (GP) model with specialized covariance functions. This GP model retains the inductive biases of the stochastic volatility model while providing the posterior predictive distribution given by GP inference. Within this framework, we take inspiration from well studied domains to introduce a new class of models, Volt and Magpie, that significantly outperform baselines in stock and wind speed forecasting, and naturally extend to the multitask setting.

ICML Conference 2021 Conference Paper

A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups

• Marc Anton Finzi
• Max Welling
• Andrew Gordon Wilson

Symmetries and equivariance are fundamental to the generalization of neural networks on domains such as images, graphs, and point clouds. Existing work has primarily focused on a small number of groups, such as the translation, rotation, and permutation groups. In this work we provide a completely general algorithm for solving for the equivariant layers of matrix groups. In addition to recovering solutions from other works as special cases, we construct multilayer perceptrons equivariant to multiple groups that have never been tackled before, including $\mathrm{O}(1, 3)$, $\mathrm{O}(5)$, $\mathrm{Sp}(n)$, and the Rubik’s cube group. Our approach outperforms non-equivariant baselines, with applications to particle physics and modeling dynamical systems. We release our software library to enable researchers to construct equivariant layers for arbitrary

ICML Conference 2021 Conference Paper

Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling

• Gregory W. Benton
• Wesley J. Maddox
• Sanae Lotfi
• Andrew Gordon Wilson

With a better understanding of the loss surfaces for multilayer networks, we can build more robust and accurate training procedures. Recently it was discovered that independently trained SGD solutions can be connected along one-dimensional paths of near-constant training loss. In this paper, we in fact demonstrate the existence of mode-connecting simplicial complexes that form multi-dimensional manifolds of low loss, connecting many independently trained models. Building on this discovery, we show how to efficiently construct simplicial complexes for fast ensembling, outperforming independently trained deep ensembles in accuracy, calibration, and robustness to dataset shift. Notably, our approach is easy to apply and only requires a few training epochs to discover a low-loss simplex.

ICML Conference 2021 Conference Paper

Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition

• Shengyang Sun
• Jiaxin Shi
• Andrew Gordon Wilson
• Roger B. Grosse

We introduce a new scalable variational Gaussian process approximation which provides a high fidelity approximation while retaining general applicability. We propose the harmonic kernel decomposition (HKD), which uses Fourier series to decompose a kernel as a sum of orthogonal kernels. Our variational approximation exploits this orthogonality to enable a large number of inducing points at a low computational cost. We demonstrate that, on a range of regression and classification problems, our approach can exploit input space symmetries such as translations and reflections, and it significantly outperforms standard variational methods in scalability and accuracy. Notably, our approach achieves state-of-the-art results on CIFAR-10 among pure GP models.

ICML Conference 2021 Conference Paper

SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes

• Sanyam Kapoor
• Marc Anton Finzi
• Ke Alexander Wang
• Andrew Gordon Wilson

State-of-the-art methods for scalable Gaussian processes use iterative algorithms, requiring fast matrix vector multiplies (MVMs) with the co-variance kernel. The Structured Kernel Interpolation (SKI) framework accelerates these MVMs by performing efficient MVMs on a grid and interpolating back to the original space. In this work, we develop a connection between SKI and the permutohedral lattice used for high-dimensional fast bilateral filtering. Using a sparse simplicial grid instead of a dense rectangular one, we can perform GP inference exponentially faster in the dimension than SKI. Our approach, Simplex-GP, enables scaling SKI to high dimensions, while maintaining strong predictive performance. We additionally provide a CUDA implementation of Simplex-GP, which enables significant GPU acceleration of MVM based inference.

ICML Conference 2021 Conference Paper

What Are Bayesian Neural Network Posteriors Really Like?

• Pavel Izmailov
• Sharad Vikram
• Matthew D. Hoffman
• Andrew Gordon Wilson

The posterior over Bayesian neural network (BNN) parameters is extremely high-dimensional and non-convex. For computational reasons, researchers approximate this posterior using inexpensive mini-batch methods such as mean-field variational inference or stochastic-gradient Markov chain Monte Carlo (SGMCMC). To investigate foundational questions in Bayesian deep learning, we instead use full batch Hamiltonian Monte Carlo (HMC) on modern architectures. We show that (1) BNNs can achieve significant performance gains over standard training and deep ensembles; (2) a single long HMC chain can provide a comparable representation of the posterior to multiple shorter chains; (3) in contrast to recent studies, we find posterior tempering is not needed for near-optimal performance, with little evidence for a “cold posterior” effect, which we show is largely an artifact of data augmentation; (4) BMA performance is robust to the choice of prior scale, and relatively similar for diagonal Gaussian, mixture of Gaussian, and logistic priors; (5) Bayesian neural networks show surprisingly poor generalization under domain shift; (6) while cheaper alternatives such as deep ensembles and SGMCMC can provide good generalization, their predictive distributions are distinct from HMC. Notably, deep ensemble predictive distributions are similarly close to HMC as standard SGLD, and closer than standard variational inference.

ICLR Conference 2020 Conference Paper

Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning

• Ruqi Zhang
• Chunyuan Li
• Jianyi Zhang
• Changyou Chen
• Andrew Gordon Wilson

The posteriors over neural network weights are high dimensional and multimodal. Each mode typically characterizes a meaningfully different representation of the data. We develop Cyclical Stochastic Gradient MCMC (SG-MCMC) to automatically explore such distributions. In particular, we propose a cyclical stepsize schedule, where larger steps discover new modes, and smaller steps characterize each mode. We prove non-asymptotic convergence theory of our proposed algorithm. Moreover, we provide extensive experimental results, including ImageNet, to demonstrate the effectiveness of cyclical SG-MCMC in learning complex multimodal distributions, especially for fully Bayesian inference with modern deep neural networks.

ICML Conference 2020 Conference Paper

Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data

• Marc Anton Finzi
• Samuel Don Stanton
• Pavel Izmailov
• Andrew Gordon Wilson

The translation equivariance of convolutional layers enables CNNs to generalize well on image problems. While translation equivariance provides a powerful inductive bias for images, we often additionally desire equivariance to other transformations, such as rotations, especially for non-image data. We propose a general method to construct a convolutional layer that is equivariant to transformations from any specified Lie group with a surjective exponential map. Incorporating equivariance to a new group requires implementing only the group exponential and logarithm maps, enabling rapid prototyping. Showcasing the simplicity and generality of our method, we apply the same model architecture to images, ball-and-stick molecular data, and Hamiltonian dynamical systems. For Hamiltonian systems, the equivariance of our models is especially impactful, leading to exact conservation of linear and angular momentum.

ICML Conference 2020 Conference Paper

Randomly Projected Additive Gaussian Processes for Regression

• Ian A. Delbridge
• David Bindel
• Andrew Gordon Wilson

Gaussian processes (GPs) provide flexible distributions over functions, with inductive biases controlled by a kernel. However, in many applications Gaussian processes can struggle with even moderate input dimensionality. Learning a low dimensional projection can help alleviate this curse of dimensionality, but introduces many trainable hyperparameters, which can be cumbersome, especially in the small data regime. We use additive sums of kernels for GP regression, where each kernel operates on a different random projection of its inputs. Surprisingly, we find that as the number of random projections increases, the predictive performance of this approach quickly converges to the performance of a kernel operating on the original full dimensional inputs, over a wide range of data sets, even if we are projecting into a single dimension. As a consequence, many problems can remarkably be reduced to one dimensional input spaces, without learning a transformation. We prove this convergence and its rate, and additionally propose a deterministic approach that converges more quickly than purely random projections. Moreover, we demonstrate our approach can achieve faster inference and improved predictive accuracy for high-dimensional inputs compared to kernels in the original input space.

ICML Conference 2020 Conference Paper

Semi-Supervised Learning with Normalizing Flows

• Pavel Izmailov
• Polina Kirichenko
• Marc Anton Finzi
• Andrew Gordon Wilson

Normalizing flows transform a latent distribution through an invertible neural network for a flexible and pleasingly simple approach to generative modelling, while preserving an exact likelihood. We propose FlowGMM, an end-to-end approach to generative semi supervised learning with normalizing flows, using a latent Gaussian mixture model. FlowGMM is distinct in its simplicity, unified treatment of labelled and unlabelled data with an exact likelihood, interpretability, and broad applicability beyond image data. We show promising results on a wide range of applications, including AG-News and Yahoo Answers text data, tabular data, and semi-supervised image classification. We also show that FlowGMM can discover interpretable structure, provide real-time optimization-free feature visualizations, and specify well calibrated predictive distributions.

NeurIPS Conference 2019 Conference Paper

A Simple Baseline for Bayesian Uncertainty in Deep Learning

• Wesley Maddox
• Pavel Izmailov
• Timur Garipov
• Dmitry Vetrov
• Andrew Gordon Wilson

We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA), which computes the first moment of stochastic gradient descent (SGD) iterates with a modified learning rate schedule, has recently been shown to improve generalization in deep learning. With SWAG, we fit a Gaussian using the SWA solution as the first moment and a low rank plus diagonal covariance also derived from the SGD iterates, forming an approximate posterior distribution over neural network weights; we then sample from this Gaussian distribution to perform Bayesian model averaging. We empirically find that SWAG approximates the shape of the true posterior, in accordance with results describing the stationary distribution of SGD iterates. Moreover, we demonstrate that SWAG performs well on a wide variety of tasks, including out of sample detection, calibration, and transfer learning, in comparison to many popular alternatives including variational inference, MC dropout, KFAC Laplace, and temperature scaling.

JMLR Journal 2019 Journal Article

Change Surfaces for Expressive Multidimensional Changepoints and Counterfactual Prediction

• William Herlands
• Daniel B. Neill
• Hannes Nickisch
• Andrew Gordon Wilson

Identifying changes in model parameters is fundamental in machine learning and statistics. However, standard changepoint models are limited in expressiveness, often addressing unidimensional problems and assuming instantaneous changes. We introduce change surfaces as a multidimensional and highly expressive generalization of changepoints. We provide a model-agnostic formalization of change surfaces, illustrating how they can provide variable, heterogeneous, and non-monotonic rates of change across multiple dimensions. Additionally, we show how change surfaces can be used for counterfactual prediction. As a concrete instantiation of the change surface framework, we develop Gaussian Process Change Surfaces (GPCS). We demonstrate counterfactual prediction with Bayesian posterior mean and credible sets, as well as massive scalability by introducing novel methods for additive non-separable kernels. Using two large spatio-temporal datasets we employ GPCS to discover and characterize complex changes that can provide scientific and policy relevant insights. Specifically, we analyze twentieth century measles incidence across the United States and discover previously unknown heterogeneous changes after the introduction of the measles vaccine. Additionally, we apply the model to requests for lead testing kits in New York City, discovering distinct spatial and demographic patterns. [abs] [ pdf ][ bib ] &copy JMLR 2019. ( edit, beta )

NeurIPS Conference 2019 Conference Paper

Exact Gaussian Processes on a Million Data Points

• Ke Wang
• Geoff Pleiss
• Jacob Gardner
• Stephen Tyree
• Kilian Weinberger
• Andrew Gordon Wilson

Gaussian processes (GPs) are flexible non-parametric models, with a capacity that grows with the available data. However, computational constraints with standard inference procedures have limited exact GPs to problems with fewer than about ten thousand training points, necessitating approximations for larger datasets. In this paper, we develop a scalable approach for exact GPs that leverages multi-GPU parallelization and methods like linear conjugate gradients, accessing the kernel matrix only through matrix multiplication. By partitioning and distributing kernel matrix multiplies, we demonstrate that an exact GP can be trained on over a million points, a task previously thought to be impossible with current computing hardware. Moreover, our approach is generally applicable, without constraints to grid data or specific kernel classes. Enabled by this scalability, we perform the first-ever comparison of exact GPs against scalable GP approximations on datasets with $10^4 \! -\! 10^6$ data points, showing dramatic performance improvements.

NeurIPS Conference 2019 Conference Paper

Function-Space Distributions over Kernels

• Gregory Benton
• Wesley Maddox
• Jayson Salkey
• Julio Albinati
• Andrew Gordon Wilson

Gaussian processes are flexible function approximators, with inductive biases controlled by a covariance kernel. Learning the kernel is the key to representation learning and strong predictive performance. In this paper, we develop functional kernel learning (FKL) to directly infer functional posteriors over kernels. In particular, we place a transformed Gaussian process over a spectral density, to induce a non-parametric distribution over kernel functions. The resulting approach enables learning of rich representations, with support for any stationary kernel, uncertainty over the values of the kernel, and an interpretable specification of a prior directly over kernels, without requiring sophisticated initialization or manual intervention. We perform inference through elliptical slice sampling, which is especially well suited to marginalizing posteriors with the strongly correlated priors typical to function space modeling. We develop our approach for non-uniform, large-scale, multi-task, and multidimensional data, and show promising performance in a wide range of settings, including interpolation, extrapolation, and kernel recovery experiments.

UAI Conference 2019 Conference Paper

Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning

• Jian Wu
• Saul Toscano-Palmerin
• Peter I. Frazier
• Andrew Gordon Wilson

Bayesian optimization is popular for optimizing time-consuming black-box objectives. Nonetheless, for hyperparameter tuning in deep neural networks, the time required to evaluate the validation error for even a few hyperparameter settings remains a bottleneck. Multi-fidelity optimization promises relief using cheaper proxies to such objectives — for example, validation error for a network trained using a subset of the training points or fewer iterations than required for convergence. We propose a highly flexible and practical approach to multi-fidelity Bayesian optimization, focused on efficiently optimizing hyperparameters for iteratively trained supervised learning models. We introduce a new acquisition function, the trace-aware knowledge-gradient, which efficiently leverages both multiple continuous fidelity controls and trace observations — values of the objective at a sequence of fidelities, available when varying fidelity using training iterations. We provide a provably convergent method for optimizing our acquisition function and show it outperforms state-of-the-art alternatives for hyperparameter tuning of deep neural networks and large-scale kernel learning.

ICML Conference 2019 Conference Paper

Simple Black-box Adversarial Attacks

• Chuan Guo 0001
• Jacob R. Gardner
• Yurong You
• Andrew Gordon Wilson
• Kilian Q. Weinberger

We propose an intriguingly simple method for the construction of adversarial images in the black-box setting. In constrast to the white-box scenario, constructing black-box adversarial images has the additional constraint on query budget, and efficient attacks remain an open problem to date. With only the mild assumption of requiring continuous-valued confidence scores, our highly query-efficient algorithm utilizes the following simple iterative principle: we randomly sample a vector from a predefined orthonormal basis and either add or subtract it to the target image. Despite its simplicity, the proposed method can be used for both untargeted and targeted attacks – resulting in previously unprecedented query efficiency in both settings. We demonstrate the efficacy and efficiency of our algorithm on several real world settings including the Google Cloud Vision API. We argue that our proposed algorithm should serve as a strong baseline for future black-box attacks, in particular because it is extremely fast and its implementation requires less than 20 lines of PyTorch code.

UAI Conference 2019 Conference Paper

Subspace Inference for Bayesian Deep Learning

• Pavel Izmailov
• Wesley J. Maddox
• Polina Kirichenko
• Timur Garipov
• Dmitry P. Vetrov
• Andrew Gordon Wilson

Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is challenging due to the high dimensionality of the parameter space. In this paper, we construct low-dimensional subspaces of parameter space, such as the first principal components of the stochastic gradient descent (SGD) trajectory, which contain diverse sets of high performing models. In these subspaces, we are able to apply elliptical slice sampling and variational inference, which struggle in the full parameter space. We show that Bayesian model averaging over the induced posterior in these subspaces produces accurate predictions and well-calibrated predictive uncertainty for both regression and image classification.

ICML Conference 2019 Conference Paper

SWALP: Stochastic Weight Averaging in Low Precision Training

• Guandao Yang
• Tianyi Zhang
• Polina Kirichenko
• Junwen Bai
• Andrew Gordon Wilson
• Christopher De Sa

Low precision operations can provide scalability, memory savings, portability, and energy efficiency. This paper proposes SWALP, an approach to low precision training that averages low-precision SGD iterates with a modified learning rate schedule. SWALP is easy to implement and can match the performance of full-precision SGD even with all numbers quantized down to 8 bits, including the gradient accumulators. Additionally, we show that SWALP converges arbitrarily close to the optimal solution for quadratic objectives, and to a noise ball asymptotically smaller than low precision SGD in strongly convex settings.

UAI Conference 2018 Conference Paper

Averaging Weights Leads to Wider Optima and Better Generalization

• Pavel Izmailov
• Dmitrii Podoprikhin
• Timur Garipov
• Dmitry P. Vetrov
• Andrew Gordon Wilson

Deep neural networks are typically trained by optimizing a loss function with an SGD variant, in conjunction with a decaying learning rate, until convergence. We show that simple averaging of multiple points along the trajectory of SGD, with a cyclical or constant learning rate, leads to better generalization than conventional training. We also show that this Stochastic Weight Averaging (SWA) procedure finds much broader optima than SGD, and approximates the recent Fast Geometric Ensembling (FGE) approach with a single model. Using SWA we achieve notable improvement in test accuracy over conventional SGD training on a range of state-of-the-art residual networks, PyramidNets, DenseNets, and ShakeShake networks on CIFAR-10, CIFAR-100, and ImageNet. In short, SWA is extremely easy to implement, improves generalization, and has almost no computational overhead.

ICML Conference 2018 Conference Paper

Constant-Time Predictive Distributions for Gaussian Processes

• Geoff Pleiss
• Jacob R. Gardner
• Kilian Q. Weinberger
• Andrew Gordon Wilson

One of the most compelling features of Gaussian process (GP) regression is its ability to provide well-calibrated posterior distributions. Recent advances in inducing point methods have sped up GP marginal likelihood and posterior mean computations, leaving posterior covariance estimation and sampling as the remaining computational bottlenecks. In this paper we address these shortcomings by using the Lanczos algorithm to rapidly approximate the predictive covariance matrix. Our approach, which we refer to as LOVE (LanczOs Variance Estimates), substantially improves time and space complexity. In our experiments, LOVE computes covariances up to 2, 000 times faster and draws samples 18, 000 times faster than existing methods, all without sacrificing accuracy.

JMLR Journal 2017 Journal Article

Learning Scalable Deep Kernels with Recurrent Structure

• Maruan Al-Shedivat
• Andrew Gordon Wilson
• Yunus Saatchi
• Zhiting Hu
• Eric P. Xing

Many applications in speech, robotics, finance, and biology deal with sequential data, where ordering matters and recurrent structures are common. However, this structure cannot be easily captured by standard kernel functions. To model such structure, we propose expressive closed-form kernel functions for Gaussian processes. The resulting model, GP-LSTM, fully encapsulates the inductive biases of long short-term memory (LSTM) recurrent networks, while retaining the non-parametric probabilistic advantages of Gaussian processes. We learn the properties of the proposed kernels by optimizing the Gaussian process marginal likelihood using a new provably convergent semi-stochastic gradient procedure, and exploit the structure of these kernels for scalable training and prediction. This approach provides a practical representation for Bayesian LSTMs. We demonstrate state-of-the-art performance on several benchmarks, and thoroughly investigate a consequential autonomous driving application, where the predictive uncertainties provided by GP- LSTM are uniquely valuable. [abs] [ pdf ][ bib ] &copy JMLR 2017. ( edit, beta )

ICML Conference 2015 Conference Paper

Fast Kronecker Inference in Gaussian Processes with non-Gaussian Likelihoods

• Seth R. Flaxman
• Andrew Gordon Wilson
• Daniel B. Neill
• Hannes Nickisch
• Alexander J. Smola

Gaussian processes (GPs) are a flexible class of methods with state of the art performance on spatial statistics applications. However, GPs require O(n^3) computations and O(n^2) storage, and popular GP kernels are typically limited to smoothing and interpolation. To address these difficulties, Kronecker methods have been used to exploit structure in the GP covariance matrix for scalability, while allowing for expressive kernel learning (Wilson et al. , 2014). However, fast Kronecker methods have been confined to Gaussian likelihoods. We propose new scalable Kronecker methods for Gaussian processes with non-Gaussian likelihoods, using a Laplace approximation which involves linear conjugate gradients for inference, and a lower bound on the GP marginal likelihood for kernel learning. Our approach has near linear scaling, requiring O(D n^(D+1)/D) operations and O(D n^2/D) storage, for n training data-points on a dense D > 1 dimensional grid. Moreover, we introduce a log Gaussian Cox process, with highly expressive kernels, for modelling spatiotemporal count processes, and apply it to a point pattern (n = 233, 088) of a decade of crime events in Chicago. Using our model, we discover spatially varying multiscale seasonal trends and produce highly accurate long-range local area forecasts.

ICML Conference 2015 Conference Paper

Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)

• Andrew Gordon Wilson
• Hannes Nickisch

We introduce a new structured kernel interpolation (SKI) framework, which generalises and unifies inducing point methods for scalable Gaussian processes (GPs). SKI methods produce kernel approximations for fast computations through kernel interpolation. The SKI framework clarifies how the quality of an inducing point approach depends on the number of inducing (aka interpolation) points, interpolation strategy, and GP covariance kernel. SKI also provides a mechanism to create new scalable kernel methods, through choosing different kernel interpolation strategies. Using SKI, with local cubic kernel interpolation, we introduce KISS-GP, which is 1) more scalable than inducing point alternatives, 2) naturally enables Kronecker and Toeplitz algebra for substantial additional gains in scalability, without requiring any grid data, and 3) can be used for fast and expressive kernel learning. KISS-GP costs O(n) time and storage for GP inference. We evaluate KISS-GP for kernel matrix approximation, kernel learning, and natural sound modelling.

ICML Conference 2013 Conference Paper

Gaussian Process Kernels for Pattern Discovery and Extrapolation

• Andrew Gordon Wilson
• Ryan P. Adams

Gaussian processes are rich distributions over functions, which provide a Bayesian nonparametric approach to smoothing and interpolation. We introduce simple closed form kernels that can be used with Gaussian processes to discover patterns and enable extrapolation. These kernels are derived by modelling a spectral density – the Fourier transform of a kernel – with a Gaussian mixture. The proposed kernels support a broad class of stationary covariances, but Gaussian process inference remains simple and analytic. We demonstrate the proposed kernels by discovering patterns and performing long range extrapolation on synthetic examples, as well as atmospheric CO2 trends and airline passenger data. We also show that it is possible to reconstruct several popular standard covariances within our framework.

ICML Conference 2012 Conference Paper

Gaussian Process Regression Networks

• Andrew Gordon Wilson
• David A. Knowles
• Zoubin Ghahramani

UAI Conference 2011 Conference Paper

Generalised Wishart Processes

• Andrew Gordon Wilson
• Zoubin Ghahramani

We introduce a new stochastic process called the generalised Wishart process (GWP). It is a collection of positive semi-definite random matrices indexed by any arbitrary input variable. We use this process as a prior over dynamic (e.g. time varying) covariance matrices. The GWP captures a diverse class of covariance dynamics, naturally handles missing data, scales nicely with dimension, has easily interpretable parameters, and can use input variables that include covariates other than time. We describe how to construct the GWP, introduce general procedures for inference and prediction, and show that it outperforms its main competitor, multivariate GARCH, even on financial data that especially suits GARCH.