Arrow Research search

Author name cluster

Jimmy Ba

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

43 papers
2 author rows

Possible papers

43

ICLR Conference 2024 Conference Paper

Identifying the Risks of LM Agents with an LM-Emulated Sandbox

  • Yangjun Ruan
  • Honghua Dong
  • Andrew Wang
  • Silviu Pitis
  • Yongchao Zhou
  • Jimmy Ba
  • Yann Dubois
  • Chris J. Maddison

Recent advances in Language Model (LM) agents and tool use, exemplified by applications like ChatGPT Plugins, enable a rich set of capabilities but also amplify potential risks—such as leaking private data or causing financial losses. Identifying these risks is labor-intensive, necessitating implementing the tools, setting up the environment for each test scenario manually, and finding risky cases. As tools and agents become more complex, the high cost of testing these agents will make it increasingly difficult to find high-stakes, long-tail risks. To address these challenges, we introduce ToolEmu: a framework that uses an LM to emulate tool execution and enables scalable testing of LM agents against a diverse range of tools and scenarios. Alongside the emulator, we develop an LM-based automatic safety evaluator that examines agent failures and quantifies associated risks. We test both the tool emulator and evaluator through human evaluation and find that 68.8% of failures identified with ToolEmu would be valid real-world agent failures. Using our curated initial benchmark consisting of 36 high-stakes toolkits and 144 test cases, we provide a quantitative risk analysis of current LM agents and identify numerous failures with potentially severe outcomes. Notably, even the safest LM agent exhibits such failures 23.9% of the time according to our evaluator, underscoring the need to develop safer LM agents for real-world deployment.

Details

ICLR Conference 2024 Conference Paper

OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text

  • Keiran Paster
  • Marco Dos Santos
  • Zhangir Azerbayev
  • Jimmy Ba

There is growing evidence that pretraining on high quality, carefully thought-out tokens such as code or mathematics plays an important role in improving the reasoning abilities of large language models. For example, Minerva, a PaLM model finetuned on billions of tokens of mathematical documents from arXiv and the web, reported dramatically improved performance on problems that require quantitative reasoning. However, because all known open source web datasets employ preprocessing that does not faithfully preserve mathematical notation, the benefits of large scale training on quantitive web documents are unavailable to the research community. We introduce OpenWebMath, an open dataset inspired by these works containing 14.7B tokens of mathematical webpages from Common Crawl. We describe in detail our method for extracting text and LaTeX content and removing boilerplate from HTML documents, as well as our methods for quality filtering and deduplication. Additionally, we run small-scale experiments by training 1.4B language models on OpenWebMath, showing that models trained on 14.7B tokens of our dataset surpass the performance of models trained on over 20x the amount of general language data. We hope that our dataset, open-sourced and released on the Hugging Face Hub, will help spur advances in the reasoning abilities of large language models.

Details

ICML Conference 2024 Conference Paper

The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning

  • Nathaniel Li
  • Alexander Pan
  • Anjali Gopal
  • Summer Yue
  • Daniel Berrios
  • Alice Gatti
  • Justin D. Li
  • Ann-Kathrin Dombrowski

The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. To measure these risks, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs. However, current evaluations are private and restricted to a narrow range of malicious use scenarios, which limits further research into reducing malicious use. To fill these gaps, we release the Weapons of Mass Destruction Proxy (WMDP) benchmark, a dataset of 3, 668 multiple-choice questions that serve as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity, and chemical security. To guide progress on unlearning, we develop RMU, a state-of-the-art unlearning method based on controlling model representations. RMU reduces model performance on WMDP while maintaining general capabilities in areas such as biology and computer science, suggesting that unlearning may be a concrete path towards reducing malicious use from LLMs. We release our benchmark and code publicly at https: //wmdp. ai.

Details

NeurIPS Conference 2023 Conference Paper

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

  • Yann Dubois
  • Chen Xuechen Li
  • Rohan Taori
  • Tianyi Zhang
  • Ishaan Gulrajani
  • Jimmy Ba
  • Carlos Guestrin
  • Percy S. Liang

Large language models (LLMs) such as ChatGPT have seen widespread adoption due to their ability to follow user instructions well. Developing these LLMs involves a complex yet poorly understood workflow requiring training with human feedback. Replicating and understanding this instruction-following process faces three major challenges: the high cost of data collection, the lack of trustworthy evaluation, and the absence of reference method implementations. We address these bottlenecks with AlpacaFarm, a simulator that enables research and development for learning from feedback at a low cost. First, we design LLM based simulator for human feedback that is 45x cheaper than crowdworkers and displays high agreement with humans. Second, we identify an evaluation dataset representative of real-world instructions and propose an automatic evaluation procedure. Third, we contribute reference implementations for several methods (PPO, best-of-n, expert iteration, among others) that learn from pairwise feedback. Finally, as an end-to-end validation of AlpacaFarm, we train and evaluate eleven models on 10k pairs of human feedback and show that rankings of models trained in AlpacaFarm match rankings of models trained on human data. As a demonstration of the research possible in AlpacaFarm, we find that methods that use a reward model can substantially improve over supervised fine-tuning and that our reference PPO implementation leads to a +10% win-rate improvement against Davinci003.

PDF Details

ICLR Conference 2023 Conference Paper

Large Language Models are Human-Level Prompt Engineers

  • Yongchao Zhou
  • Andrei Ioan Muresanu
  • Ziwen Han
  • Keiran Paster
  • Silviu Pitis
  • Harris Chan
  • Jimmy Ba

By conditioning on natural language instructions, large language models (LLMs) have displayed impressive capabilities as general-purpose computers. However, task performance depends significantly on the quality of the prompt used to steer the model, and most effective prompts have been handcrafted by humans. Inspired by classical program synthesis and the human approach to prompt engineering, we propose Automatic Prompt Engineer (APE) for automatic instruction generation and selection. In our method, we treat the instruction as the "program," optimized by searching over a pool of instruction candidates proposed by an LLM in order to maximize a chosen score function. To evaluate the quality of the selected instruction, we evaluate the zero-shot performance of another LLM following the selected instruction. Experiments on 24 NLP tasks show that our automatically generated instructions outperform the prior LLM baseline by a large margin and achieve better or comparable performance to the instructions generated by human annotators on 21/24 tasks. We conduct extensive qualitative and quantitative analyses to explore the performance of APE. We show that APE-engineered prompts can be applied to steer models toward truthfulness and/or informativeness, as well as to improve few-shot learning performance by simply prepending them to standard in-context learning prompts.

Details

NeurIPS Conference 2023 Conference Paper

Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective

  • Jimmy Ba
  • Murat A. Erdogdu
  • Taiji Suzuki
  • Zhichao Wang
  • Denny Wu

We consider the learning of a single-index target function $f_*: \mathbb{R}^d\to\mathbb{R}$ under spiked covariance data: $$f_*(\boldsymbol{x}) = \textstyle\sigma_*(\frac{1}{\sqrt{1+\theta}}\langle\boldsymbol{x}, \boldsymbol{\mu}\rangle), ~~ \boldsymbol{x}\overset{\small\mathrm{i. i. d. }}{\sim}\mathcal{N}(0, \boldsymbol{I_d} + \theta\boldsymbol{\mu}\boldsymbol{\mu}^\top), ~~ \theta\asymp d^{\beta} \text{ for } \beta\in[0, 1), $$ where the link function $\sigma_*: \mathbb{R}\to\mathbb{R}$ is a degree-$p$ polynomial with information exponent $k$ (defined as the lowest degree in the Hermite expansion of $\sigma_*$), and it depends on the projection of input $\boldsymbol{x}$ onto the spike (signal) direction $\boldsymbol{\mu}\in\mathbb{R}^d$. In the proportional asymptotic limit where the number of training examples $n$ and the dimensionality $d$ jointly diverge: $n, d\to\infty, n/d\to\psi\in(0, \infty)$, we ask the following question: how large should the spike magnitude $\theta$ (i. e. , the strength of the low-dimensional component) be, in order for $(i)$ kernel methods, $(ii)$ neural networks optimized by gradient descent, to learn $f_*$? We show that for kernel ridge regression, $\beta\ge 1-\frac{1}{p}$ is both sufficient and necessary. Whereas for two-layer neural networks trained with gradient descent, $\beta>1-\frac{1}{k}$ suffices. Our results demonstrate that both kernel methods and neural networks benefit from low-dimensional structures in the data. Further, since $k\le p$ by definition, neural networks can adapt to such structures more effectively.

PDF Details

ICLR Conference 2023 Conference Paper

Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve

  • Juhan Bae
  • Michael R. Zhang
  • Michael Ruan
  • Eric Wang
  • So Hasegawa
  • Jimmy Ba
  • Roger B. Grosse

Variational autoencoders (VAEs) are powerful tools for learning latent representations of data used in a wide range of applications. In practice, VAEs usually require multiple training rounds to choose the amount of information the latent variable should retain. This trade-off between the reconstruction error (distortion) and the KL divergence (rate) is typically parameterized by a hyperparameter $\beta$. In this paper, we introduce Multi-Rate VAE (MR-VAE), a computationally efficient framework for learning optimal parameters corresponding to various $\beta$ in a single training run. The key idea is to explicitly formulate a response function using hypernetworks that maps $\beta$ to the optimal parameters. MR-VAEs construct a compact response hypernetwork where the pre-activations are conditionally gated based on $\beta$. We justify the proposed architecture by analyzing linear VAEs and showing that it can represent response functions exactly for linear VAEs. With the learned hypernetwork, MR-VAEs can construct the rate-distortion curve without additional training and can be deployed with significantly less hyperparameter tuning. Empirically, our approach is competitive and often exceeds the performance of multiple $\beta$-VAEs training with minimal computation and memory overheads.

Details

NeurIPS Conference 2023 Conference Paper

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

  • Shalev Lifshitz
  • Keiran Paster
  • Harris Chan
  • Jimmy Ba
  • Sheila McIlraith

Constructing AI models that respond to text instructions is challenging, especially for sequential decision-making tasks. This work introduces a methodology, inspired by unCLIP, for instruction-tuning generative models of behavior without relying on a large dataset of instruction-labeled trajectories. Using this methodology, we create an instruction-tuned Video Pretraining (VPT) model called STEVE-1, which can follow short-horizon open-ended text and visual instructions in Minecraft. STEVE-1 is trained in two steps: adapting the pretrained VPT model to follow commands in MineCLIP's latent space, then training a prior to predict latent codes from text. This allows us to finetune VPT through self-supervised behavioral cloning and hindsight relabeling, reducing the need for costly human text annotations, and all for only $60 of compute. By leveraging pretrained models like VPT and MineCLIP and employing best practices from text-conditioned image generation, STEVE-1 sets a new bar for open-ended instruction following in Minecraft with low-level controls (mouse and keyboard) and raw pixel inputs, far outperforming previous baselines and robustly completing 12 of 13 tasks in our early-game evaluation suite. We provide experimental evidence highlighting key factors for downstream performance, including pretraining, classifier-free guidance, and data scaling. All resources, including our model weights, training scripts, and evaluation tools are made available for further research.

PDF Details

ICML Conference 2023 Conference Paper

TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation

  • Zhaoyan Liu
  • Noël Vouitsis
  • Satya Krishna Gorti
  • Jimmy Ba
  • Gabriel Loaiza-Ganem

We propose TR0N, a highly general framework to turn pre-trained unconditional generative models, such as GANs and VAEs, into conditional models. The conditioning can be highly arbitrary, and requires only a pre-trained auxiliary model. For example, we show how to turn unconditional models into class-conditional ones with the help of a classifier, and also into text-to-image models by leveraging CLIP. TR0N learns a lightweight stochastic mapping which "translates’" between the space of conditions and the latent space of the generative model, in such a way that the generated latent corresponds to a data sample satisfying the desired condition. The translated latent samples are then further improved upon through Langevin dynamics, enabling us to obtain higher-quality data samples. TR0N requires no training data nor fine-tuning, yet can achieve a zero-shot FID of 10. 9 on MS-COCO, outperforming competing alternatives not only on this metric, but also in sampling speed – all while retaining a much higher level of generality. Our code is available at https: //github. com/layer6ai-labs/tr0n.

Details

NeurIPS Conference 2022 Conference Paper

Dataset Distillation using Neural Feature Regression

  • Yongchao Zhou
  • Ehsan Nezhadarya
  • Jimmy Ba

Dataset distillation aims to learn a small synthetic dataset that preserves most of the information from the original dataset. Dataset distillation can be formulated as a bi-level meta-learning problem where the outer loop optimizes the meta-dataset and the inner loop trains a model on the distilled data. Meta-gradient computation is one of the key challenges in this formulation, as differentiating through the inner loop learning procedure introduces significant computation and memory costs. In this paper, we address these challenges using neural Feature Regression with Pooling (FRePo), achieving the state-of-the-art performance with an order of magnitude less memory requirement and two orders of magnitude faster training than previous methods. The proposed algorithm is analogous to truncated backpropagation through time with a pool of models to alleviate various types of overfitting in dataset distillation. FRePo significantly outperforms the previous methods on CIFAR100, Tiny ImageNet, and ImageNet-1K. Furthermore, we show that high-quality distilled data can greatly improve various downstream applications, such as continual learning and membership inference defense. Please check out our webpage at https: //sites. google. com/view/frepo.

PDF Details

NeurIPS Conference 2022 Conference Paper

High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation

  • Jimmy Ba
  • Murat A. Erdogdu
  • Taiji Suzuki
  • Zhichao Wang
  • Denny Wu
  • Greg Yang

We study the first gradient descent step on the first-layer parameters $\boldsymbol{W}$ in a two-layer neural network: $f(\boldsymbol{x}) = \frac{1}{\sqrt{N}}\boldsymbol{a}^\top\sigma(\boldsymbol{W}^\top\boldsymbol{x})$, where $\boldsymbol{W}\in\mathbb{R}^{d\times N}, \boldsymbol{a}\in\mathbb{R}^{N}$ are randomly initialized, and the training objective is the empirical MSE loss: $\frac{1}{n}\sum_{i=1}^n (f(\boldsymbol{x}_i)-y_i)^2$. In the proportional asymptotic limit where $n, d, N\to\infty$ at the same rate, and an idealized student-teacher setting where the teacher $f^*$ is a single-index model, we compute the prediction risk of ridge regression on the conjugate kernel after one gradient step on $\boldsymbol{W}$ with learning rate $\eta$. We consider two scalings of the first step learning rate $\eta$. For small $\eta$, we establish a Gaussian equivalence property for the trained feature map, and prove that the learned kernel improves upon the initial random features model, but cannot defeat the best linear model on the input. Whereas for sufficiently large $\eta$, we prove that for certain $f^*$, the same ridge estimator on trained features can go beyond this ``linear regime'' and outperform a wide range of (fixed) kernels. Our results demonstrate that even one gradient step can lead to a considerable advantage over random features, and highlight the role of learning rate scaling in the initial phase of training.

PDF Details

ICLR Conference 2022 Conference Paper

Understanding the Variance Collapse of SVGD in High Dimensions

  • Jimmy Ba
  • Murat A. Erdogdu
  • Marzyeh Ghassemi
  • Shengyang Sun
  • Taiji Suzuki
  • Denny Wu
  • Tianzong Zhang

Stein variational gradient descent (SVGD) is a deterministic inference algorithm that evolves a set of particles to fit a target distribution. Despite its computational efficiency, SVGD often underestimates the variance of the target distribution in high dimensions. In this work we attempt to explain the variance collapse in SVGD. On the qualitative side, we compare the SVGD update with gradient descent on the maximum mean discrepancy (MMD) objective; we observe that the variance collapse phenomenon relates to the bias from deterministic updates present in the "driving force" of SVGD, and empirically verify that removal of such bias leads to more accurate variance estimation. On the quantitative side, we demonstrate that the variance collapse of SVGD can be accurately predicted in the proportional asymptotic limit, i.e., when the number of particles $n$ and dimensions $d$ diverge at the same rate. In particular, for learning high-dimensional isotropic Gaussians, we derive the exact equilibrium variance for both SVGD and MMD-descent under certain near-orthogonality assumption on the converged particles, and confirm that SVGD suffers from the "curse of dimensionality".

Details

NeurIPS Conference 2022 Conference Paper

You Can’t Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments

  • Keiran Paster
  • Sheila McIlraith
  • Jimmy Ba

Recently, methods such as Decision Transformer that reduce reinforcement learning to a prediction task and solve it via supervised learning (RvS) have become popular due to their simplicity, robustness to hyperparameters, and strong overall performance on offline RL tasks. However, simply conditioning a probabilistic model on a desired return and taking the predicted action can fail dramatically in stochastic environments since trajectories that result in a return may have only achieved that return due to luck. In this work, we describe the limitations of RvS approaches in stochastic environments and propose a solution. Rather than simply conditioning on returns, as is standard practice, our proposed method, ESPER, conditions on learned average returns which are independent from environment stochasticity. Doing so allows ESPER to achieve strong alignment between target return and expected performance in real environments. We demonstrate this in several challenging stochastic offline-RL tasks including the challenging puzzle game 2048, and Connect Four playing against a stochastic opponent. In all tested domains, ESPER achieves significantly better alignment between the target return and achieved return than simply conditioning on returns. ESPER also achieves higher maximum performance than even the value-based baselines.

PDF Details

NeurIPS Conference 2021 Conference Paper

Clockwork Variational Autoencoders

  • Vaibhav Saxena
  • Jimmy Ba
  • Danijar Hafner

Deep learning has enabled algorithms to generate realistic images. However, accurately predicting long video sequences requires understanding long-term dependencies and remains an open challenge. While existing video prediction models succeed at generating sharp images, they tend to fail at accurately predicting far into the future. We introduce the Clockwork VAE (CW-VAE), a video prediction model that leverages a hierarchy of latent sequences, where higher levels tick at slower intervals. We demonstrate the benefits of both hierarchical latents and temporal abstraction on 4 diverse video prediction datasets with sequences of up to 1000 frames, where CW-VAE outperforms top video prediction models. Additionally, we propose a Minecraft benchmark for long-term video prediction. We conduct several experiments to gain insights into CW-VAE and confirm that slower levels learn to represent objects that change more slowly in the video, and faster levels learn to represent faster objects.

PDF Details

ICML Conference 2021 Conference Paper

Efficient Statistical Tests: A Neural Tangent Kernel Approach

  • Sheng Jia
  • Ehsan Nezhadarya
  • Yuhuai Wu
  • Jimmy Ba

For machine learning models to make reliable predictions in deployment, one needs to ensure the previously unknown test samples need to be sufficiently similar to the training data. The commonly used shift-invariant kernels do not have the compositionality and fail to capture invariances in high-dimensional data in computer vision. We propose a shift-invariant convolutional neural tangent kernel (SCNTK) based outlier detector and two-sample tests with maximum mean discrepancy (MMD) that is O(n) in the number of samples due to using the random feature approximation. On MNIST and CIFAR10 with various types of dataset shifts, we empirically show that statistical tests with such compositional kernels, inherited from infinitely wide neural networks, achieve higher detection accuracy than existing non-parametric methods. Our method also provides a competitive alternative to adapted kernel methods that require a training phase.

Details

NeurIPS Conference 2021 Conference Paper

How does a Neural Network's Architecture Impact its Robustness to Noisy Labels?

  • Jingling Li
  • Mozhi Zhang
  • Keyulu Xu
  • John Dickerson
  • Jimmy Ba

Noisy labels are inevitable in large real-world datasets. In this work, we explore an area understudied by previous works --- how the network's architecture impacts its robustness to noisy labels. We provide a formal framework connecting the robustness of a network to the alignments between its architecture and target/noise functions. Our framework measures a network's robustness via the predictive power in its representations --- the test performance of a linear model trained on the learned representations using a small set of clean labels. We hypothesize that a network is more robust to noisy labels if its architecture is more aligned with the target function than the noise. To support our hypothesis, we provide both theoretical and empirical evidence across various neural network architectures and different domains. We also find that when the network is well-aligned with the target function, its predictive power in representations could improve upon state-of-the-art (SOTA) noisy-label-training methods in terms of test accuracy and even outperform sophisticated methods that use clean labels.

PDF Details

ICLR Conference 2021 Conference Paper

INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving

  • Yuhuai Wu
  • Albert Q. Jiang
  • Jimmy Ba
  • Roger B. Grosse

In learning-assisted theorem proving, one of the most critical challenges is to generalize to theorems unlike those seen at training time. In this paper, we introduce INT, an INequality Theorem proving benchmark designed to test agents’ generalization ability. INT is based on a theorem generator, which provides theoretically infinite data and allows us to measure 6 different types of generalization, each reflecting a distinct challenge, characteristic of automated theorem proving. In addition, provides a fast theorem proving environment with sequence-based and graph-based interfaces, conducive to performing learning-based research. We introduce base-lines with architectures including transformers and graph neural networks (GNNs)for INT. Using INT, we find that transformer-based agents achieve stronger test performance for most of the generalization tasks, despite having much larger out-of-distribution generalization gaps than GNNs. We further find that the addition of Monte Carlo Tree Search (MCTS) at test time helps to prove new theorems.

Details

NeurIPS Conference 2021 Conference Paper

Learning Domain Invariant Representations in Goal-conditioned Block MDPs

  • Beining Han
  • Chongyi Zheng
  • Harris Chan
  • Keiran Paster
  • Michael Zhang
  • Jimmy Ba

Deep Reinforcement Learning (RL) is successful in solving many complex Markov Decision Processes (MDPs) problems. However, agents often face unanticipated environmental changes after deployment in the real world. These changes are often spurious and unrelated to the underlying problem, such as background shifts for visual input agents. Unfortunately, deep RL policies are usually sensitive to these changes and fail to act robustly against them. This resembles the problem of domain generalization in supervised learning. In this work, we study this problem for goal-conditioned RL agents. We propose a theoretical framework in the Block MDP setting that characterizes the generalizability of goal-conditioned policies to new environments. Under this framework, we develop a practical method PA-SkewFit that enhances domain generalization. The empirical evaluation shows that our goal-conditioned RL agent can perform well in various unseen test environments, improving by 50\% over baselines.

PDF Details

ICML Conference 2021 Conference Paper

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning

  • Yuhuai Wu
  • Markus N. Rabe
  • Wenda Li
  • Jimmy Ba
  • Roger B. Grosse
  • Christian Szegedy

While designing inductive bias in neural architectures has been widely studied, we hypothesize that transformer networks are flexible enough to learn inductive bias from suitable generic tasks. Here, we replace architecture engineering by encoding inductive bias in the form of datasets. Inspired by Peirce’s view that deduction, induction, and abduction are the primitives of reasoning, we design three synthetic tasks that are intended to require the model to have these three abilities. We specifically design these tasks to be synthetic and devoid of mathematical knowledge to ensure that only the fundamental reasoning biases can be learned from these tasks. This defines a new pre-training methodology called "LIME" (Learning Inductive bias for Mathematical rEasoning). Models trained with LIME significantly outperform vanilla transformers on four very different large mathematical reasoning benchmarks. Unlike dominating the computation cost as traditional pre-training approaches, LIME requires only a small fraction of the computation cost of the typical downstream task. The code for generating LIME tasks is available at https: //github. com/tonywu95/LIME.

Details

ICLR Conference 2021 Conference Paper

Mastering Atari with Discrete World Models

  • Danijar Hafner
  • Timothy P. Lillicrap
  • Mohammad Norouzi 0002
  • Jimmy Ba

Intelligent agents need to generalize from past experience to achieve goals in complex environments. World models facilitate such generalization and allow learning behaviors from imagined outcomes to increase sample-efficiency. While learning world models from image inputs has recently become feasible for some tasks, modeling Atari games accurately enough to derive successful behaviors has remained an open challenge for many years. We introduce DreamerV2, a reinforcement learning agent that learns behaviors purely from predictions in the compact latent space of a powerful world model. The world model uses discrete representations and is trained separately from the policy. DreamerV2 constitutes the first agent that achieves human-level performance on the Atari benchmark of 55 tasks by learning behaviors inside a separately trained world model. With the same computational budget and wall-clock time, Dreamer V2 reaches 200M frames and surpasses the final performance of the top single-GPU agents IQN and Rainbow. DreamerV2 is also applicable to tasks with continuous actions, where it learns an accurate world model of a complex humanoid robot and solves stand-up and walking from only pixel inputs.

Details

ICLR Conference 2021 Conference Paper

Planning from Pixels using Inverse Dynamics Models

  • Keiran Paster
  • Sheila A. McIlraith
  • Jimmy Ba

Learning dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn models in a latent space by learning to predict sequences of future actions conditioned on task completion. These models track task-relevant environment dynamics over a distribution of tasks, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches.

Details

ICLR Conference 2021 Conference Paper

When does preconditioning help or hurt generalization?

  • Shun-ichi Amari
  • Jimmy Ba
  • Roger B. Grosse
  • Xuechen Li 0005
  • Atsushi Nitanda
  • Taiji Suzuki
  • Denny Wu
  • Ji Xu

While second order optimizers such as natural gradient descent (NGD) often speed up optimization, their effect on generalization has been called into question. This work presents a more nuanced view on how the \textit{implicit bias} of optimizers affects the comparison of generalization properties. We provide an exact asymptotic bias-variance decomposition of the generalization error of preconditioned ridgeless regression in the overparameterized regime, and consider the inverse population Fisher information matrix (used in NGD) as a particular example. We determine the optimal preconditioner $\boldsymbol{P}$ for both the bias and variance, and find that the relative generalization performance of different optimizers depends on label noise and ``shape'' of the signal (true parameters): when the labels are noisy, the model is misspecified, or the signal is misaligned with the features, NGD can achieve lower risk; conversely, GD generalizes better under clean labels, a well-specified model, or aligned signal. Based on this analysis, we discuss several approaches to manage the bias-variance tradeoff, and the potential benefit of interpolating between first- and second-order updates. We then extend our analysis to regression in the reproducing kernel Hilbert space and demonstrate that preconditioning can lead to more efficient decrease in the population risk. Lastly, we empirically compare the generalization error of first- and second-order optimizers in neural network experiments, and observe robust trends matching our theoretical analysis.

Details

ICLR Conference 2020 Conference Paper

An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality

  • Silviu Pitis
  • Harris Chan
  • Kiarash Jamali
  • Jimmy Ba

Distances are pervasive in machine learning. They serve as similarity measures, loss functions, and learning targets; it is said that a good distance measure solves a task. When defining distances, the triangle inequality has proven to be a useful constraint, both theoretically---to prove convergence and optimality guarantees---and empirically---as an inductive bias. Deep metric learning architectures that respect the triangle inequality rely, almost exclusively, on Euclidean distance in the latent space. Though effective, this fails to model two broad classes of subadditive distances, common in graphs and reinforcement learning: asymmetric metrics, and metrics that cannot be embedded into Euclidean space. To address these problems, we introduce novel architectures that are guaranteed to satisfy the triangle inequality. We prove our architectures universally approximate norm-induced metrics on $\mathbb{R}^n$, and present a similar result for modified Input Convex Neural Networks. We show that our architectures outperform existing metric approaches when modeling graph distances and have a better inductive bias than non-metric approaches when training data is limited in the multi-goal reinforcement learning setting.

Details

ICLR Conference 2020 Conference Paper

BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong Learning

  • Yeming Wen
  • Dustin Tran
  • Jimmy Ba

Ensembles, where multiple neural networks are trained individually and their predictions are averaged, have been shown to be widely successful for improving both the accuracy and predictive uncertainty of single neural networks. However, an ensemble’s cost for both training and testing increases linearly with the number of networks, which quickly becomes untenable. In this paper, we propose BatchEnsemble, an ensemble method whose computational and memory costs are significantly lower than typical ensembles. BatchEnsemble achieves this by defining each weight matrix to be the Hadamard product of a shared weight among all ensemble members and a rank-one matrix per member. Unlike ensembles, BatchEnsemble is not only parallelizable across devices, where one device trains one member, but also parallelizable within a device, where multiple ensemble members are updated simultaneously for a given mini-batch. Across CIFAR-10, CIFAR-100, WMT14 EN-DE/EN-FR translation, and out-of-distribution tasks, BatchEnsemble yields competitive accuracy and uncertainties as typical ensembles; the speedup at test time is 3X and memory reduction is 3X at an ensemble of size 4. We also apply BatchEnsemble to lifelong learning, where on Split-CIFAR-100, BatchEnsemble yields comparable performance to progressive neural networks while having a much lower computational and memory costs. We further show that BatchEnsemble can easily scale up to lifelong learning on Split-ImageNet which involves 100 sequential learning tasks

Details

ICLR Conference 2020 Conference Paper

Dream to Control: Learning Behaviors by Latent Imagination

  • Danijar Hafner
  • Timothy P. Lillicrap
  • Jimmy Ba
  • Mohammad Norouzi 0002

Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for deriving behaviors from them. We present Dreamer, a reinforcement learning agent that solves long-horizon tasks from images purely by latent imagination. We efficiently learn behaviors by propagating analytic gradients of learned state values back through trajectories imagined in the compact state space of a learned world model. On 20 challenging visual control tasks, Dreamer exceeds existing approaches in data-efficiency, computation time, and final performance.

Details

ICLR Conference 2020 Conference Paper

Exploring Model-based Planning with Policy Networks

  • Tingwu Wang
  • Jimmy Ba

Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in both sample efficiency and asymptotic performance. Despite the successes, the existing planning methods search from candidate sequences randomly generated in the action space, which is inefficient in complex high-dimensional environments. In this paper, we propose a novel MBRL algorithm, model-based policy planning (POPLIN), that combines policy networks with online planning. More specifically, we formulate action planning at each time-step as an optimization problem using neural networks. We experiment with both optimization w.r.t. the action sequences initialized from the policy network, and also online optimization directly w.r.t. the parameters of the policy network. We show that POPLIN obtains state-of-the-art performance in the MuJoCo benchmarking environments, being about 3x more sample efficient than the state-of-the-art algorithms, such as PETS, TD3 and SAC. To explain the effectiveness of our algorithm, we show that the optimization surface in parameter space is smoother than in action space. Further more, we found the distilled policy network can be effectively applied without the expansive model predictive control during test time for some environments such as Cheetah. Code is released.

Details

ICLR Conference 2020 Conference Paper

Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint

  • Jimmy Ba
  • Murat A. Erdogdu
  • Taiji Suzuki
  • Denny Wu
  • Tianzong Zhang

This paper investigates the generalization properties of two-layer neural networks in high-dimensions, i.e. when the number of samples $n$, features $d$, and neurons $h$ tend to infinity at the same rate. Specifically, we derive the exact population risk of the unregularized least squares regression problem with two-layer neural networks when either the first or the second layer is trained using a gradient flow under different initialization setups. When only the second layer coefficients are optimized, we recover the \textit{double descent} phenomenon: a cusp in the population risk appears at $h\approx n$ and further overparameterization decreases the risk. In contrast, when the first layer weights are optimized, we highlight how different scales of initialization lead to different inductive bias, and show that the resulting risk is \textit{independent} of overparameterization. Our theoretical and experimental results suggest that previously studied model setups that provably give rise to \textit{double descent} might not translate to optimizing two-layer neural networks.

Details

ICML Conference 2020 Conference Paper

Improving Transformer Optimization Through Better Initialization

  • Xiao Shi Huang
  • Felipe Pérez
  • Jimmy Ba
  • Maksims Volkovs

The Transformer architecture has achieved considerable success recently; the key component of the Transformer is the attention layer that enables the model to focus on important regions within an input sequence. Gradient optimization with attention layers can be notoriously difficult requiring tricks such as learning rate warmup to prevent divergence. As Transformer models are becoming larger and more expensive to train, recent research has focused on understanding and improving optimization in these architectures. In this work our contributions are two-fold: we first investigate and empirically validate the source of optimization problems in the encoder-decoder Transformer architecture; we then propose a new weight initialization scheme with theoretical justification, that enables training without warmup or layer normalization. Empirical results on public machine translation benchmarks show that our approach achieves leading accuracy, allowing to train deep Transformer models with 200 layers in both encoder and decoder (over 1000 attention/MLP blocks) without difficulty. Code for this work is available here: \url{https: //github. com/layer6ai-labs/T-Fixup}.

Details

UAI Conference 2020 Conference Paper

Learning Intrinsic Rewards as a Bi-Level Optimization Problem

  • Bradly C. Stadie
  • Lunjun Zhang
  • Jimmy Ba

We reinterpret the problem of finding intrinsic rewards in reinforcement learning (RL) as a bilevel optimization problem. Using this interpretation, we can make use of recent advancements in the hyperparameter optimization literature, mainly from Self-Tuning Networks (STN), to learn intrinsic rewards. To facilitate our methods, we introduces a new general conditioning layer: Conditional Layer Normalization (CLN). We evaluate our method on several continuous control benchmarks in the Mujoco physics simulator. On all of these benchmarks, the intrinsic rewards learned on the fly lead to higher final rewards.

Details

ICML Conference 2020 Conference Paper

Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning

  • Silviu Pitis
  • Harris Chan
  • Stephen Zhao
  • Bradly C. Stadie
  • Jimmy Ba

What goals should a multi-goal reinforcement learning agent pursue during training in long-horizon tasks? When the desired (test time) goal distribution is too distant to offer a useful learning signal, we argue that the agent should not pursue unobtainable goals. Instead, it should set its own intrinsic goals that maximize the entropy of the historical achieved goal distribution. We propose to optimize this objective by having the agent pursue past achieved goals in sparsely explored areas of the goal space, which focuses exploration on the frontier of the achievable goal set. We show that our strategy achieves an order of magnitude better sample efficiency than the prior state of the art on long-horizon multi-goal tasks including maze navigation and block stacking.

Details

ICLR Conference 2020 Conference Paper

On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach

  • Yuanhao Wang 0001
  • Guodong Zhang 0006
  • Jimmy Ba

Many tasks in modern machine learning can be formulated as finding equilibria in sequential games. In particular, two-player zero-sum sequential games, also known as minimax optimization, have received growing interest. It is tempting to apply gradient descent to solve minimax optimization given its popularity and success in supervised learning. However, it has been noted that naive application of gradient descent fails to find some local minimax and can converge to non-local-minimax points. In this paper, we propose Follow-the-Ridge (FR), a novel algorithm that provably converges to and only converges to local minimax. We show theoretically that the algorithm addresses the notorious rotational behaviour of gradient dynamics, and is compatible with preconditioning and positive momentum. Empirically, FR solves toy minimax problems and improves the convergence of GAN training compared to the recent minimax optimization algorithms.

Details

NeurIPS Conference 2019 Conference Paper

Graph Normalizing Flows

  • Jenny Liu
  • Aviral Kumar
  • Jimmy Ba
  • Jamie Kiros
  • Kevin Swersky

We introduce graph normalizing flows: a new, reversible graph neural network model for prediction and generation. On supervised tasks, graph normalizing flows perform similarly to message passing neural networks, but at a significantly reduced memory footprint, allowing them to scale to larger graphs. In the unsupervised case, we combine graph normalizing flows with a novel graph auto-encoder to create a generative model of graph structures. Our model is permutation-invariant, generating entire graphs with a single feed-forward pass, and achieves competitive results with the state-of-the art auto-regressive models, while being better suited to parallel computing architectures.

PDF Details

NeurIPS Conference 2019 Conference Paper

Lookahead Optimizer: k steps forward, 1 step back

  • Michael Zhang
  • James Lucas
  • Jimmy Ba
  • Geoffrey Hinton

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate schemes, such as AdaGrad and Adam and (2) accelerated schemes, such as heavy-ball and Nesterov momentum. In this paper, we propose a new optimization algorithm, Lookahead, that is orthogonal to these previous approaches and iteratively updates two sets of weights. Intuitively, the algorithm chooses a search direction by looking ahead at the sequence of ``fast weights" generated by another optimizer. We show that Lookahead improves the learning stability and lowers the variance of its inner optimizer with negligible computation and memory cost. We empirically demonstrate Lookahead can significantly improve the performance of SGD and Adam, even with their default hyperparameter settings on ImageNet, CIFAR-10/100, neural machine translation, and Penn Treebank.

PDF Details

RLDM Conference 2019 Conference Abstract

ProtoGE: Prototype Goal Encodings for Multi-goal Reinforcement Learning

  • Silviu Pitis
  • Harris Chan
  • Jimmy Ba

Current approaches to multi-goal reinforcement learning train the agent directly on the desired goal space. When goals are sparse, binary and coarsely defined, with each goal representing a set of states, this has at least two downsides. First, transitions between different goals may be sparse, making it difficult for the agent to obtain useful control signals, even using Hindsight Experience Replay. Second, having trained only on the desired goal representation, it is difficult to transfer learning to other goal spaces. We propose the following simple idea: instead of training on the desired coarse goal space, substitute it with a finer—more specific—goal space, perhaps even the agent’s state space (the “state-goal” space), and use Prototype Goal Encodings (”ProtoGE”) to encode coarse goals as fine ones. This has several advantages. First, an agent trained on an appropriately fine goal space receives more descriptive control signals and can learn to accomplish goals in its desired goal space significantly faster. Second, finer goal representations are more flexible and allow for efficient transfer. The state-goal representation in particular, is universal: an agent trained on the state-goal space can potentially adapt to arbitrary goals, so long as a Protoge map is available. We provide empirical evidence for the above claims and establish a new state-of-the-art in standard multi-goal MuJoCo environments.

PDF Details

NeurIPS Conference 2018 Conference Paper

On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

  • Maziar Sanjabi
  • Jimmy Ba
  • Meisam Razaviyayn
  • Jason Lee

Generative Adversarial Networks (GANs) are one of the most practical methods for learning data distributions. A popular GAN formulation is based on the use of Wasserstein distance as a metric between probability distributions. Unfortunately, minimizing the Wasserstein distance between the data distribution and the generative model distribution is a computationally challenging problem as its objective is non-convex, non-smooth, and even hard to compute. In this work, we show that obtaining gradient information of the smoothed Wasserstein GAN formulation, which is based on regularized Optimal Transport (OT), is computationally effortless and hence one can apply first order optimization methods to minimize this objective. Consequently, we establish theoretical convergence guarantee to stationarity for a proposed class of GAN optimization algorithms. Unlike the original non-smooth formulation, our algorithm only requires solving the discriminator to approximate optimality. We apply our method to learning MNIST digits as well as CIFAR-10 images. Our experiments show that our method is computationally efficient and generates images comparable to the state of the art algorithms given the same architecture and computational power.

PDF Details

NeurIPS Conference 2018 Conference Paper

Reversible Recurrent Neural Networks

  • Matthew MacKay
  • Paul Vicol
  • Jimmy Ba
  • Roger Grosse

Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the hidden-to-hidden transition can be reversed---offer a path to reduce the memory requirements of training, as hidden states need not be stored and instead can be recomputed during backpropagation. We first show that perfectly reversible RNNs, which require no storage of the hidden activations, are fundamentally limited because they cannot forget information from their hidden state. We then provide a scheme for storing a small number of bits in order to allow perfect reversal with forgetting. Our method achieves comparable performance to traditional models while reducing the activation memory cost by a factor of 10--15. We extend our technique to attention-based sequence-to-sequence models, where it maintains performance while reducing activation memory cost by a factor of 5--10 in the encoder, and a factor of 10--15 in the decoder.

PDF Details

NeurIPS Conference 2017 Conference Paper

Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

  • Yuhuai Wu
  • Elman Mansimov
  • Roger Grosse
  • Shun Liao
  • Jimmy Ba

In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient and propose to optimize both the actor and the critic using Kronecker-factored approximate curvature (K-FAC) with trust region; hence we call our method Actor Critic using Kronecker-Factored Trust Region (ACKTR). To the best of our knowledge, this is the first scalable trust region natural gradient method for actor-critic methods. It is also the method that learns non-trivial tasks in continuous control as well as discrete control policies directly from raw pixel inputs. We tested our approach across discrete domains in Atari games as well as continuous domains in the MuJoCo environment. With the proposed methods, we are able to achieve higher rewards and a 2- to 3-fold improvement in sample efficiency on average, compared to previous state-of-the-art on-policy actor-critic methods. Code is available at https: //github. com/openai/baselines

PDF Details

ICLR Conference 2016 Conference Paper

Generating Images from Captions with Attention

  • Elman Mansimov
  • Emilio Parisotto
  • Jimmy Ba
  • Ruslan Salakhutdinov

Motivated by the recent progress in generative models, we introduce a model that generates images from natural language descriptions. The proposed model iteratively draws patches on a canvas, while attending to the relevant words in the description. After training on Microsoft COCO, we compare our model with several baseline generative models on image generation and retrieval tasks. We demonstrate that our model produces higher quality samples than other approaches and generates images with novel scene compositions corresponding to previously unseen captions in the dataset.

Details

NeurIPS Conference 2016 Conference Paper

Using Fast Weights to Attend to the Recent Past

  • Jimmy Ba
  • Geoffrey Hinton
  • Volodymyr Mnih
  • Joel Leibo
  • Catalin Ionescu

Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs. There is no good reason for this restriction. Synapses have dynamics at many different time-scales and this suggests that artificial neural networks might benefit from variables that change slower than activities but much faster than the standard weights. These ``fast weights'' can be used to store temporary memories of the recent past and they provide a neurally plausible way of implementing the type of attention to the past that has recently proven helpful in sequence-to-sequence models. By using fast weights we can avoid the need to store copies of neural activity patterns.

PDF Details

NeurIPS Conference 2015 Conference Paper

Learning Wake-Sleep Recurrent Attention Models

  • Jimmy Ba
  • Russ Salakhutdinov
  • Roger Grosse
  • Brendan Frey

Despite their success, convolutional neural networks are computationally expensive because they must examine all image locations. Stochastic attention-based models have been shown to improve computational efficiency at test time, but they remain difficult to train because of intractable posterior inference and high variance in the stochastic gradient estimates. Borrowing techniques from the literature on training deep generative models, we present the Wake-Sleep Recurrent Attention Model, a method for training stochastic attention networks which improves posterior inference and which reduces the variability in the stochastic gradients. We show that our method can greatly speed up the training time for stochastic attention networks in the domains of image classification and caption generation.

PDF Details

ICML Conference 2015 Conference Paper

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

  • Kelvin Xu
  • Jimmy Ba
  • Jamie Kiros
  • Kyunghyun Cho
  • Aaron C. Courville
  • Ruslan Salakhutdinov
  • Richard S. Zemel
  • Yoshua Bengio

Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images. We describe how we can train this model in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound. We also show through visualization how the model is able to automatically learn to fix its gaze on salient objects while generating the corresponding words in the output sequence. We validate the use of attention with state-of-the-art performance on three benchmark datasets: Flickr8k, Flickr30k and MS COCO.

Details

NeurIPS Conference 2014 Conference Paper

Do Deep Nets Really Need to be Deep?

  • Jimmy Ba
  • Rich Caruana

Currently, deep neural networks are the state of the art on problems such as speech recognition and computer vision. In this paper we empirically demonstrate that shallow feed-forward nets can learn the complex functions previously learned by deep nets and achieve accuracies previously only achievable with deep models. Moreover, in some cases the shallow nets can learn these deep functions using the same number of parameters as the original deep models. On the TIMIT phoneme recognition and CIFAR-10 image recognition tasks, shallow nets can be trained that perform similarly to complex, well-engineered, deeper convolutional models.

PDF Details

NeurIPS Conference 2013 Conference Paper

Adaptive dropout for training deep neural networks

  • Jimmy Ba
  • Brendan Frey

Recently, it was shown that by dropping out hidden activities with a probability of 0. 5, deep neural networks can perform very well. We describe a model in which a binary belief network is overlaid on a neural network and is used to decrease the information content of its hidden units by selectively setting activities to zero. This ''dropout network can be trained jointly with the neural network by approximately computing local expectations of binary dropout variables, computing derivatives using back-propagation, and using stochastic gradient descent. Interestingly, experiments show that the learnt dropout network parameters recapitulate the neural network parameters, suggesting that a good dropout network regularizes activities according to magnitude. When evaluated on the MNIST and NORB datasets, we found our method can be used to achieve lower classification error rates than other feather learning methods, including standard dropout, denoising auto-encoders, and restricted Boltzmann machines. For example, our model achieves 5. 8% error on the NORB test set, which is better than state-of-the-art results obtained using convolutional architectures. "

PDF Details