Arrow Research search

Author name cluster

Sepp Hochreiter

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.

47 papers
2 author rows

Possible papers

47

ICML Conference 2025 Conference Paper

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

  • Thomas Schmied
  • Thomas Adler
  • Vihang Prakash Patil
  • Maximilian Beck
  • Korbinian Pöppel
  • Johannes Brandstetter
  • Günter Klambauer
  • Razvan Pascanu

In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-scale datasets via sequence modeling. Existing models are primarily based on the Transformer architecture, which results in powerful agents. However, due to slow inference times, Transformer-based approaches are impractical for real-time applications, such as robotics. Recently, modern recurrent architectures, such as xLSTM and Mamba, have been proposed that exhibit parallelization benefits during training similar to the Transformer architecture while offering fast inference. In this work, we study the aptitude of these modern recurrent architectures for large action models. Consequently, we propose a Large Recurrent Action Model (LRAM) with an xLSTM at its core that comes with linear-time inference complexity and natural sequence length extrapolation abilities. Experiments on 432 tasks from 6 domains show that LRAM compares favorably to Transformers in terms of performance and speed.

Details

ICLR Conference 2025 Conference Paper

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences

  • Niklas Schmidinger
  • Lisa Schneckenreiter
  • Philipp Seidl
  • Johannes Schimunek
  • Pieter-Jan Hoedt
  • Johannes Brandstetter
  • Andreas Mayr
  • Sohvi Luukkonen

Language models for biological and chemical sequences enable crucial applications such as drug discovery, protein engineering, and precision medicine. Currently, these language models are predominantly based on Transformer architectures. While Transformers have yielded impressive results, their quadratic runtime dependency on sequence length complicates their use for long genomic sequences and in-context learning on proteins and chemical sequences. Recently, the recurrent xLSTM architecture has been shown to perform favorably compared to Transformers and modern state-space models (SSMs) in the natural language domain. Similar to SSMs, xLSTMs have linear runtime dependency and allow for constant-memory decoding at inference time, which makes them prime candidates for modeling long-range dependencies in biological and chemical sequences. In this work, we tailor xLSTM towards these domains and we propose a suite of language models called Bio-xLSTM. Extensive experiments in three large domains, genomics, proteins, and chemistry, were performed to assess xLSTM’s ability to model biological and chemical sequences. The results show that Bio-xLSTM is a highly proficient generative model for DNA, protein, and chemical sequences, learns rich representations, and can perform in-context learning for proteins and small molecules.

Details

ICLR Conference 2025 Conference Paper

FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware

  • Korbinian Pöppel
  • Maximilian Beck
  • Sepp Hochreiter

While Transformers and other sequence-parallelizable neural network architectures seem like the current state of the art in sequence modeling, they specifically lack state-tracking capabilities. These are important for time-series tasks and logical reasoning. Traditional RNNs like LSTMs and GRUs, as well as modern variants like sLSTM do have these capabilities at the cost of strictly sequential processing. While this is often seen as a strong limitation, we show how fast these networks can get with our hardware-optimization FlashRNN in Triton and CUDA, optimizing kernels to the register level on modern GPUs. We extend traditional RNNs with a parallelization variant that processes multiple RNNs of smaller hidden state in parallel, similar to the head-wise processing in Transformers. To enable flexibility on different GPU variants, we introduce a new optimization framework for hardware-internal cache sizes, memory and compute handling. It models the hardware in a setting using polyhedral-like constraints, including the notion of divisibility. This speeds up the solution process in our ConstrINT library for general integer constraint satisfaction problems (integer CSPs). We show that our kernels can achieve 50x speed-ups over a vanilla PyTorch implementation and allow 40x larger hidden sizes compared to our Triton implementation. We have open-sourced our kernels and the optimization library to boost research in the direction of state-tracking enabled RNNs and sequence modeling here: https://github.com/NX-AI/flashrnn

Details

ICML Conference 2025 Conference Paper

Geometry-Informed Neural Networks

  • Arturs Berzins
  • Andreas Radler
  • Eric Volkmann
  • Sebastian Sanokowski
  • Sepp Hochreiter
  • Johannes Brandstetter

Geometry is a ubiquitous tool in computer graphics, design, and engineering. However, the lack of large shape datasets limits the application of state-of-the-art supervised learning methods and motivates the exploration of alternative learning strategies. To this end, we introduce geometry-informed neural networks (GINNs) – a framework for training shape-generative neural fields without data by leveraging user-specified design requirements in the form of objectives and constraints. By adding diversity as an explicit constraint, GINNs avoid mode-collapse and can generate multiple diverse solutions, often required in geometry tasks. Experimentally, we apply GINNs to several problems spanning physics, geometry, and engineering design, showing control over geometrical and topological properties, such as surface smoothness or the number of holes. These results demonstrate the potential of training shape-generative models without data, paving the way for new generative design approaches without large datasets.

Details

ICLR Conference 2025 Conference Paper

Improving Uncertainty Estimation through Semantically Diverse Language Generation

  • Lukas Aichberger
  • Kajetan Schweighofer
  • Mykyta Ielanskyi
  • Sepp Hochreiter

Large language models (LLMs) can suffer from hallucinations when generating text. These hallucinations impede various applications in society and industry by making LLMs untrustworthy. Current LLMs generate text in an autoregressive fashion by predicting and appending text tokens. When an LLM is uncertain about the semantic meaning of the next tokens to generate, it is likely to start hallucinating. Thus, it has been suggested that predictive uncertainty is one of the main causes of hallucinations. We introduce Semantically Diverse Language Generation (SDLG) to quantify predictive uncertainty in LLMs. SDLG steers the LLM to generate semantically diverse yet likely alternatives for an initially generated text. This approach provides a precise measure of aleatoric semantic uncertainty, detecting whether the initial text is likely to be hallucinated. Experiments on question-answering tasks demonstrate that SDLG consistently outperforms existing methods while being the most computationally efficient, setting a new standard for uncertainty estimation in LLMs.

Details

ICLR Conference 2025 Conference Paper

MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Masked Image Modeling Representations

  • Benedikt Alkin
  • Lukas Miklautz
  • Sepp Hochreiter
  • Johannes Brandstetter

We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations within MIM models generally reside in intermediate layers. Accordingly, MIM-Refiner leverages multiple instance discrimination (ID) heads that are connected to different intermediate layers. In each head, a nearest neighbor ID objective constructs clusters that capture semantic information which improves performance on downstream tasks, including off-the-shelf and fine-tuning settings. The refinement process is short and simple - yet highly effective. Within a few epochs, we refine the features of MIM models from subpar to state-of-the-art, off-the-shelf features. Refining a ViT-H, pre-trained with data2vec 2.0 on ImageNet-1K, sets a new state-of-the-art in linear probing (84.7\%) and low-shot classification among models that are pre-trained on ImageNet-1K. MIM-Refiner efficiently combines the advantages of MIM and ID objectives, enabling scaling ID objectives to billion parameter models using relatively little compute. MIM-Refiner compares favorably against previous state-of-the-art SSL models on various benchmarks such as low-shot classification, long-tailed classification and semantic segmentation.

Details

UAI Conference 2025 Conference Paper

On Information-Theoretic Measures of Predictive Uncertainty

  • Kajetan Schweighofer
  • Lukas Aichberger
  • Mykyta Ielanskyi
  • Sepp Hochreiter

Reliable estimation of predictive uncertainty is crucial for machine learning applications, particularly in high-stakes scenarios where hedging against risks is essential. Despite its significance, there is no universal agreement on how to best quantify predictive uncertainty. In this work, we revisit core concepts to propose a framework for information-theoretic measures of predictive uncertainty. Our proposed framework categorizes predictive uncertainty measures according to two factors: (I) The predicting model (II) The approximation of the true predictive distribution. Examining all possible combinations of these two factors, we derive a set of predictive uncertainty measures that includes both known and newly introduced ones. We extensively evaluate these measures across a broad set of tasks, identifying conditions under which certain measures excel. Our findings show the importance of aligning the choice of uncertainty measure with the predicting model on in-distribution (ID) data, the limitations of epistemic uncertainty measures for out-of-distribution (OOD) data, and that the disentanglement between measures varies substantially between ID and OOD data. Together, these insights provide a more comprehensive understanding of predictive uncertainty measures, revealing their implicit assumptions and relationships.

Details

NeurIPS Conference 2025 Conference Paper

Parameter Efficient Fine-tuning via Explained Variance Adaptation

  • Fabian Paischer
  • Lukas Hauzenberger
  • Thomas Schmied
  • Benedikt Alkin
  • Marc Deisenroth
  • Sepp Hochreiter

Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned for a specific downstream task. The most common fine-tuning method is to update pretrained weights via low-rank adaptation (LoRA). Existing initialization strategies for LoRA often rely on singular value decompositions (SVD) of gradients or weight matrices. However, they do not provably maximize the expected gradient signal, which is critical for fast adaptation. To this end, we introduce E xplained V ariance A daptation (EVA), an initialization scheme that uses the directions capturing the most activation variance, provably maximizing the expected gradient signal and accelerating fine-tuning. EVA performs incremental SVD on minibatches of activation vectors and selects the right-singular vectors for initialization once they converged. Further, by selecting the directions that capture the most activation-variance for a given rank budget, EVA accommodates adaptive ranks that reduce the number of trainable parameters. We apply EVA to a variety of fine-tuning tasks as language generation and understanding, image classification, and reinforcement learning. EVA exhibits faster convergence than competitors and achieves the highest average score across a multitude of tasks per domain while reducing the number of trainable parameters through rank redistribution. In summary, EVA establishes a new Pareto frontier compared to existing LoRA initialization schemes in both accuracy and efficiency.

PDF Details

NeurIPS Conference 2025 Conference Paper

pLSTM: parallelizable Linear Source Transition Mark networks

  • Korbinian Pöppel
  • Richard Freinschlag
  • Thomas Schmied
  • Wei Lin
  • Sepp Hochreiter

Modern recurrent architectures, such as xLSTM and Mamba, have recently challenged the Transformer in language modeling. However, their structure constrains their applicability to sequences only or requires processing multi-dimensional data structures, such as images or molecular graphs, in a pre-defined sequential order. In contrast, Multi-Dimensional RNNs (MDRNNs) are well suited for data with a higher level structure, like 2D grids, trees, and directed acyclic graphs (DAGs). In this work, we extend the notion of multi-dimensionality to linear RNNs. We introduce parallelizable Linear Source Transition Mark networks (pLSTMs) using Source, Transition, and Mark gates that act on the linegraph of a general DAG. This enables parallelization in analogy to parallel associative scans and the chunkwise-recurrent form of sequential linear RNNs, but for DAGs. For regular grids (1D and 2D), like images, this scheme can be efficiently implemented using einsum operations, concatenations, and padding in logarithmic time. pLSTMs tackle the vanishing/exploding activation/gradient problem for long distances in DAGs via two distinct modes: a directed propagation mode (P-mode) and a diffusive distribution mode (D-mode). To showcase the long-range capabilities of pLSTM, we introduce arrow-pointing extrapolation as a synthetic computer vision task that contains long-distance directional information. We demonstrate that pLSTMs generalize well to larger image sizes, whereas Transformers struggle to extrapolate. On established molecular graph and computer vision benchmarks, pLSTMs also show strong performance. The complete code is available at https: //github. com/ml-jku/plstm_experiments.

PDF Details

NeurIPS Conference 2025 Conference Paper

Rethinking Losses for Diffusion Bridge Samplers

  • Sebastian Sanokowski
  • Lukas Gruber
  • Christoph Bartmann
  • Sepp Hochreiter
  • Sebastian Lehner

Diffusion bridges are a promising class of deep-learning methods for sampling from unnormalized distributions. Recent works show that the Log Variance (LV) loss consistently outperforms the reverse Kullback-Leibler (rKL) loss when using the reparametrization trick to compute rKL-gradients. While the on-policy LV loss yields identical gradients to the rKL loss when combined with the log-derivative trick for diffusion samplers with non-learnable forward processes, this equivalence does not hold for diffusion bridges or when diffusion coefficients are learned. Based on this insight we argue that for diffusion bridges the LV loss does not represent an optimization objective that can be motivated like the rKL loss via the data processing inequality. Our analysis shows that employing the rKL loss with the log-derivative trick (rKL-LD) does not only avoid these conceptual problems but also consistently outperforms the LV loss. Experimental results with different types of diffusion bridges on challenging benchmarks show that samplers trained with the rKL-LD loss achieve better performance. From a practical perspective we find that rKL-LD requires significantly less hyperparameter optimization and yields more stable training behavior.

PDF Details

ICLR Conference 2025 Conference Paper

Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics

  • Sebastian Sanokowski
  • Wilhelm Franz Berghammer
  • Haoyu Peter Wang
  • Martin Ennemoser
  • Sepp Hochreiter
  • Sebastian Lehner

Learning to sample from complex unnormalized distributions over discrete domains emerged as a promising research direction with applications in statistical physics, variational inference, and combinatorial optimization. Recent work has demonstrated the potential of diffusion models in this domain. However, existing methods face limitations in memory scaling and thus the number of attainable diffusion steps since they require backpropagation through the entire generative process. To overcome these limitations we introduce two novel training methods for discrete diffusion samplers, one grounded in the policy gradient theorem and the other one leveraging Self-Normalized Neural Importance Sampling (SN-NIS). These methods yield memory-efficient training and achieve state-of-the-art results in unsupervised combinatorial optimization. Numerous scientific applications additionally require the ability of unbiased sampling. We introduce adaptations of SN-NIS and Neural Markov Chain Monte Carlo that enable for the first time the application of discrete diffusion models to this problem. We validate our methods on Ising model benchmarks and find that they outperform popular autoregressive approaches. Our work opens new avenues for applying diffusion models to a wide range of scientific applications in discrete domains that were hitherto restricted to exact likelihood models.

Details

ICML Conference 2025 Conference Paper

The Disparate Benefits of Deep Ensembles

  • Kajetan Schweighofer
  • Adrián Arnaiz-Rodríguez
  • Sepp Hochreiter
  • Nuria Oliver

Ensembles of Deep Neural Networks, Deep Ensembles, are widely used as a simple way to boost predictive performance. However, their impact on algorithmic fairness is not well understood yet. Algorithmic fairness examines how a model’s performance varies across socially relevant groups defined by protected attributes such as age, gender, or race. In this work, we explore the interplay between the performance gains from Deep Ensembles and fairness. Our analysis reveals that they unevenly favor different groups, a phenomenon that we term the disparate benefits effect. We empirically investigate this effect using popular facial analysis and medical imaging datasets with protected group attributes and find that it affects multiple established group fairness metrics, including statistical parity and equal opportunity. Furthermore, we identify that the per-group differences in predictive diversity of ensemble members can explain this effect. Finally, we demonstrate that the classical Hardt post-processing method is particularly effective at mitigating the disparate benefits effect of Deep Ensembles by leveraging their better-calibrated predictive distributions.

Details

NeurIPS Conference 2025 Conference Paper

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels

  • Maximilian Beck
  • Korbinian Pöppel
  • Phillip Lippe
  • Sepp Hochreiter

Linear RNNs with gating recently demonstrated competitive performance compared to Transformers in language modeling. Although their linear compute scaling in sequence length offers theoretical runtime advantages over Transformers, realizing these benefits in practice requires optimized custom kernels, as Transformers rely on the highly efficient Flash Attention kernels (Dao, 2024). Leveraging the chunkwise-parallel formulation of linear RNNs, Flash Linear Attention (FLA) (Yang & Zhang, 2024) shows that linear RNN kernels are faster than Flash Attention, by parallelizing over chunks of the input sequence. However, since the chunk size of FLA is limited, many intermediate states must be materialized in GPU memory. This leads to low arithmetic intensity and causes high memory consumption and IO cost, especially for long-context pre-training. In this work, we present Tiled Flash Linear Attention (TFLA), a novel kernel algorithm for linear RNNs, that enables arbitrary large chunk sizes and high arithmetic intensity by introducing an additional level of sequence parallelization within each chunk. First, we apply TFLA to the xLSTM with matrix memory, the mLSTM (Beck et al. , 2024). Second, we propose an mLSTM variant with sigmoid input gate and reduced computation for even faster kernel runtimes at equal language modeling performance. In our speed benchmarks, we show that our new mLSTM kernels based on TFLA outperform highly optimized Flash Attention, Linear Attention and Mamba kernels, setting a new state of the art for efficient long-context sequence modeling primitives. Our code is available at: https: //github. com/NX-AI/mlstm_kernels

PDF Details

NeurIPS Conference 2025 Conference Paper

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

  • Andreas Auer
  • Patrick Podest
  • Daniel Klotz
  • Sebastian Böck
  • Günter Klambauer
  • Sepp Hochreiter

In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero-shot prediction, where past values serve as context for forecasting future values, making powerful forecasting tools accessible to non-experts and increasing the performance when training data are scarce. Most existing zero-shot forecasting approaches rely on transformer architectures, which, despite their success in language, often fall short of expectations in time series forecasting, where recurrent models like LSTMs frequently have the edge. Conversely, while LSTMs are well-suited for time series modeling due to their state-tracking capabilities, they lack strong in-context learning abilities. We introduce TiRex that closes this gap by leveraging xLSTM, an enhanced LSTM with competitive in-context learning skills. Unlike transformers, state-space models, or parallelizable RNNs such as RWKV, TiRex retains state tracking, a critical property for long-horizon forecasting. To further facilitate its state-tracking ability, we propose a training-time masking strategy called CPM. TiRex sets a new state of the art in zero-shot time series forecasting on the Hugging Face benchmarks GiftEval and Chronos-ZS, outperforming significantly larger models including TabPFN-TS (Prior Labs), Chronos Bolt (Amazon), TimesFM (Google), and Moirai (Salesforce) across both short- and long-term forecasts.

PDF Details

ICLR Conference 2025 Conference Paper

Vision-LSTM: xLSTM as Generic Vision Backbone

  • Benedikt Alkin
  • Maximilian Beck
  • Korbinian Pöppel
  • Sepp Hochreiter
  • Johannes Brandstetter

Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has been extended to a scalable and performant architecture - the xLSTM - which overcomes long-standing LSTM limitations via exponential gating and parallelizable matrix memory structure. In this paper, we introduce Vision-LSTM (ViL), an adaption of the xLSTM building blocks to computer vision. ViL comprises a stack of xLSTM blocks where odd blocks process the sequence of patch tokens from top to bottom while even blocks go from bottom to top. ViL achieves strong performances on classification, transfer learning and segmentation tasks as well as a beneficial pre-training cost-to-performance trade-off. Experiments show that ViL holds promise to be further deployed as new generic backbone for computer vision architectures.

Details

ICML Conference 2025 Conference Paper

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

  • Maximilian Beck
  • Korbinian Pöppel
  • Phillip Lippe
  • Richard Kurle
  • Patrick M. Blies
  • Günter Klambauer
  • Sebastian Böck
  • Sepp Hochreiter

Recent breakthroughs in solving reasoning, math and coding problems with Large Language Models (LLMs) have been enabled by investing substantial computation budgets at inference time. Therefore, inference speed is one of the most critical properties of LLM architectures, and there is a growing need for LLMs that are efficient and fast at inference. Recently, LLMs built on the xLSTM architecture have emerged as a powerful alternative to Transformers, offering linear compute scaling with sequence length and constant memory usage, both highly desirable properties for efficient inference. However, such xLSTM-based LLMs have yet to be scaled to larger models and assessed and compared with respect to inference speed and efficiency. In this work, we introduce xLSTM 7B, a 7-billion-parameter LLM that combines xLSTM’s architectural benefits with targeted optimizations for fast and efficient inference. Our experiments demonstrate that xLSTM 7B achieves performance on downstream tasks comparable to other similar-sized LLMs, while providing significantly faster inference speeds and greater efficiency compared to Llama- and Mamba-based LLMs. These results establish xLSTM 7B as the fastest and most efficient 7B LLM, offering a solution for tasks that require large amounts of test-time computation. Our work highlights xLSTM’s potential as a foundational architecture for methods building on heavy use of LLM inference. Our model weights, model code and training code are open-source. Model: https: //huggingface. co/NX-AI/xLSTM-7b Code: https: //github. com/NX-AI/xlstm and https: //github. com/NX-AI/xlstm-jax.

Details

ICML Conference 2024 Conference Paper

A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization

  • Sebastian Sanokowski
  • Sepp Hochreiter
  • Sebastian Lehner

Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based approaches rely primarily on generative models that yield exact sample likelihoods. This work introduces a method that lifts this restriction and opens the possibility to employ highly expressive latent variable models like diffusion models. Our approach is conceptually based on a loss that upper bounds the reverse Kullback-Leibler divergence and evades the requirement of exact sample likelihoods. We experimentally validate our approach in data-free Combinatorial Optimization and demonstrate that our method achieves a new state-of-the-art on a wide range of benchmark problems.

Details

AAAI Conference 2024 Conference Paper

Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget

  • Johannes Lehner
  • Benedikt Alkin
  • Andreas Fürst
  • Elisabeth Rumetshofer
  • Lukas Miklautz
  • Sepp Hochreiter

Masked Image Modeling (MIM) methods, like Masked Autoencoders (MAE), efficiently learn a rich representation of the input. However, for adapting to downstream tasks, they require a sufficient amount of labeled data since their rich features code not only objects but also less relevant image background. In contrast, Instance Discrimination (ID) methods focus on objects. In this work, we study how to combine the efficiency and scalability of MIM with the ability of ID to perform downstream classification in the absence of large amounts of labeled data. To this end, we introduce Masked Autoencoder Contrastive Tuning (MAE-CT), a sequential approach that utilizes the implicit clustering of the Nearest Neighbor Contrastive Learning (NNCLR) objective to induce abstraction in the topmost layers of a pre-trained MAE. MAE-CT tunes the rich features such that they form semantic clusters of objects without using any labels. Notably, MAE-CT does not rely on hand-crafted augmentations and frequently achieves its best performances while using only minimal augmentations (crop & flip). Further, MAE-CT is compute efficient as it requires at most 10% overhead compared to MAE re-training. Applied to large and huge Vision Transformer (ViT) models, MAE-CT excels over previous self-supervised methods trained on ImageNet in linear probing, k-NN and low-shot classification accuracy as well as in unsupervised clustering accuracy. With ViT-H/16 MAE-CT achieves a new state-of-the-art in linear probing of 82.2%. Project page: github.com/ml-jku/MAE-CT.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Energy-based Hopfield Boosting for Out-of-Distribution Detection

  • Claus Hofmann
  • Simon Schmid
  • Bernhard Lehner
  • Daniel Klotz
  • Sepp Hochreiter

Out-of-distribution (OOD) detection is critical when deploying machine learning models in the real world. Outlier exposure methods, which incorporate auxiliary outlier data in the training process, can drastically improve OOD detection performance compared to approaches without advanced training strategies. We introduce Hopfield Boosting, a boosting approach, which leverages modern Hopfield energy to sharpen the decision boundary between the in-distribution and OOD data. Hopfield Boosting encourages the model to focus on hard-to-distinguish auxiliary outlier examples that lie close to the decision boundary between in-distribution and auxiliary outlier data. Our method achieves a new state-of-the-art in OOD detection with outlier exposure, improving the FPR95 from 2. 28 to 0. 92 on CIFAR-10, from 11. 76 to 7. 94 on CIFAR-100, and from 50. 74 to 36. 60 on ImageNet-1K.

PDF Details DOI

ICML Conference 2024 Conference Paper

Overcoming Saturation in Density Ratio Estimation by Iterated Regularization

  • Lukas Gruber
  • Markus Holzleitner
  • Johannes Lehner
  • Sepp Hochreiter
  • Werner Zellinger

Estimating the ratio of two probability densities from finitely many samples, is a central task in machine learning and statistics. In this work, we show that a large class of kernel methods for density ratio estimation suffers from error saturation, which prevents algorithms from achieving fast error convergence rates on highly regular learning problems. To resolve saturation, we introduce iterated regularization in density ratio estimation to achieve fast error rates. Our methods outperform its non-iteratively regularized versions on benchmarks for density ratio estimation as well as on large-scale evaluations for importance-weighted ensembling of deep unsupervised domain adaptation models.

Details

NeurIPS Conference 2024 Conference Paper

xLSTM: Extended Long Short-Term Memory

  • Maximilian Beck
  • Korbinian Pöppel
  • Markus Spanring
  • Andreas Auer
  • Oleksandra Prudnikova
  • Michael Kopp
  • Günter Klambauer
  • Johannes Brandstetter

In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since then, LSTMs have stood the test of time and contributed to numerous deep learning success stories, in particular they constituted the first Large Language Models (LLMs). However, the advent of the Transformer technology with parallelizable self-attention at its core marked the dawn of a new era, outpacing LSTMs at scale. We now raise a simple question: How far do we get in language modeling when scaling LSTMs to billions of parameters, leveraging the latest techniques from modern LLMs, but mitigating known limitations of LSTMs? Firstly, we introduce exponential gating with appropriate normalization and stabilization techniques. Secondly, we modify the LSTM memory structure, obtaining: (i) sLSTM with a scalar memory, a scalar update, and new memory mixing, (ii) mLSTM that is fully parallelizable with a matrix memory and a covariance update rule. Integrating these LSTM extensions into residual block backbones yields xLSTM blocks that are then residually stacked into xLSTM architectures. Exponential gating and modified memory structures boost xLSTM capabilities to perform favorably when compared to state-of-the-art Transformers and State Space Models, both in performance and scaling.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation

  • Marius-Constantin Dinu
  • Markus Holzleitner
  • Maximilian Beck
  • Hoan Duc Nguyen
  • Andrea Huber
  • Hamid Eghbal-Zadeh
  • Bernhard Alois Moser
  • Sergei V. Pereverzyev

We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the strategy to compute several models using different hyper-parameters, and, to subsequently compute a linear aggregation of the models. While several heuristics exist that follow this strategy, methods are still missing that rely on thorough theories for bounding the target error. In this turn, we propose a method that extends weighted least squares to vector-valued functions, e.g., deep neural networks. We show that the target error of the proposed algorithm is asymptotically not worse than twice the error of the unknown optimal aggregation. We also perform a large scale empirical comparative study on several datasets, including text, images, electroencephalogram, body sensor signals and signals from mobile phones. Our method outperforms deep embedded validation (DEV) and importance weighted validation (IWV) on all datasets, setting a new state-of-the-art performance for solving parameter choice issues in unsupervised domain adaptation with theoretical error guarantees. We further study several competitive heuristics, all outperforming IWV and DEV on at least five datasets. However, our method outperforms each heuristic on at least five of seven datasets.

Details

AAAI Conference 2023 Conference Paper

Boundary Graph Neural Networks for 3D Simulations

  • Andreas Mayr
  • Sebastian Lehner
  • Arno Mayrhofer
  • Christoph Kloss
  • Sepp Hochreiter
  • Johannes Brandstetter

The abundance of data has given machine learning considerable momentum in natural sciences and engineering, though modeling of physical processes is often difficult. A particularly tough problem is the efficient representation of geometric boundaries. Triangularized geometric boundaries are well understood and ubiquitous in engineering applications. However, it is notoriously difficult to integrate them into machine learning approaches due to their heterogeneity with respect to size and orientation. In this work, we introduce an effective theory to model particle-boundary interactions, which leads to our new Boundary Graph Neural Networks (BGNNs) that dynamically modify graph structures to obey boundary conditions. The new BGNNs are tested on complex 3D granular flow processes of hoppers, rotating drums and mixers, which are all standard components of modern industrial machinery but still have complicated geometry. BGNNs are evaluated in terms of computational efficiency as well as prediction accuracy of particle flows and mixing entropies. BGNNs are able to accurately reproduce 3D granular flows within simulation uncertainties over hundreds of thousands of simulation timesteps. Most notably, in our experiments, particles stay within the geometric objects without using handcrafted conditions or restrictions.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Conformal Prediction for Time Series with Modern Hopfield Networks

  • Andreas Auer
  • Martin Gauch
  • Daniel Klotz
  • Sepp Hochreiter

To quantify uncertainty, conformal prediction methods are gaining continuously more interest and have already been successfully applied to various domains. However, they are difficult to apply to time series as the autocorrelative structure of time series violates basic assumptions required by conformal prediction. We propose HopCPT, a novel conformal prediction approach for time series that not only copes with temporal structures but leverages them. We show that our approach is theoretically well justified for time series where temporal dependencies are present. In experiments, we demonstrate that our new approach outperforms state-of-the-art conformal prediction methods on multiple real-world time series datasets from four different domains.

PDF Details

ICLR Conference 2023 Conference Paper

Context-enriched molecule representations improve few-shot drug discovery

  • Johannes Schimunek
  • Philipp Seidl
  • Lukas Friedrich
  • Daniel Kuhn
  • Friedrich Rippmann
  • Sepp Hochreiter
  • Günter Klambauer

A central task in computational drug discovery is to construct models from known active molecules to find further promising molecules for subsequent screening. However, typically only very few active molecules are known. Therefore, few-shot learning methods have the potential to improve the effectiveness of this critical phase of the drug discovery process. We introduce a new method for few-shot drug discovery. Its main idea is to enrich a molecule representation by knowledge about known context or reference molecules. Our novel concept for molecule representation enrichment is to associate molecules from both the support set and the query set with a large set of reference (context) molecules through a modern Hopfield network. Intuitively, this enrichment step is analogous to a human expert who would associate a given molecule with familiar molecules whose properties are known. The enrichment step reinforces and amplifies the covariance structure of the data, while simultaneously removing spurious correlations arising from the decoration of molecules. Our approach is compared with other few-shot methods for drug discovery on the FS-Mol benchmark dataset. On FS-Mol, our approach outperforms all compared methods and therefore sets a new state-of-the art for few-shot learning in drug discovery. An ablation study shows that the enrichment step of our method is the key to improve the predictive quality. In a domain shift experiment, we further demonstrate the robustness of our method.

Details

ICML Conference 2023 Conference Paper

Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language

  • Philipp Seidl
  • Andreu Vall
  • Sepp Hochreiter
  • Günter Klambauer

Activity and property prediction models are the central workhorses in drug discovery and materials sciences, but currently, they have to be trained or fine-tuned for new tasks. Without training or fine-tuning, scientific language models could be used for such low-data tasks through their announced zero- and few-shot capabilities. However, their predictive quality at activity prediction is lacking. In this work, we envision a novel type of activity prediction model that is able to adapt to new prediction tasks at inference time, via understanding textual information describing the task. To this end, we propose a new architecture with separate modules for chemical and natural language inputs, and a contrastive pretraining objective on data from large biochemical databases. In extensive experiments, we show that our method CLAMP yields improved predictive performance on few-shot learning benchmarks and zero-shot problems in drug discovery. We attribute the advances of our method to the modularized architecture and to our pre-training objective.

Details

NeurIPS Conference 2023 Conference Paper

Learning to Modulate pre-trained Models in RL

  • Thomas Schmied
  • Markus Hofmarcher
  • Fabian Paischer
  • Razvan Pascanu
  • Sepp Hochreiter

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In supervised learning, this adaptation problem is addressed by large-scale pre-training followed by fine-tuning to new down-stream tasks. Recently, pre-training on multiple tasks has been gaining traction in RL. However, fine-tuning a pre-trained model often suffers from catastrophic forgetting. That is, the performance on the pre-training tasks deteriorates when fine-tuning on new tasks. To investigate the catastrophic forgetting phenomenon, we first jointly pre-train a model on datasets from two benchmark suites, namely Meta-World and DMControl. Then, we evaluate and compare a variety of fine-tuning methods prevalent in natural language processing, both in terms of performance on new tasks, and how well performance on pre-training tasks is retained. Our study shows that with most fine-tuning approaches, the performance on pre-training tasks deteriorates significantly. Therefore, we propose a novel method, Learning-to-Modulate (L2M), that avoids the degradation of learned skills by modulating the information flow of the frozen pre-trained model via a learnable modulation pool. Our method achieves state-of-the-art performance on the Continual-World benchmark, while retaining performance on the pre-training tasks. Finally, to aid future research in this area, we release a dataset encompassing 50 Meta-World and 16 DMControl tasks.

PDF Details

NeurIPS Conference 2023 Conference Paper

Quantification of Uncertainty with Adversarial Models

  • Kajetan Schweighofer
  • Lukas Aichberger
  • Mykyta Ielanskyi
  • Günter Klambauer
  • Sepp Hochreiter

Quantifying uncertainty is important for actionable predictions in real-world applications. A crucial part of predictive uncertainty quantification is the estimation of epistemic uncertainty, which is defined as an integral of the product between a divergence function and the posterior. Current methods such as Deep Ensembles or MC dropout underperform at estimating the epistemic uncertainty, since they primarily consider the posterior when sampling models. We suggest Quantification of Uncertainty with Adversarial Models (QUAM) to better estimate the epistemic uncertainty. QUAM identifies regions where the whole product under the integral is large, not just the posterior. Consequently, QUAM has lower approximation error of the epistemic uncertainty compared to previous methods. Models for which the product is large correspond to adversarial models (not adversarial examples! ). Adversarial models have both a high posterior as well as a high divergence between their predictions and that of a reference model. Our experiments show that QUAM excels in capturing epistemic uncertainty for deep learning models and outperforms previous methods on challenging tasks in the vision domain.

PDF Details

NeurIPS Conference 2023 Conference Paper

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

  • Fabian Paischer
  • Thomas Adler
  • Markus Hofmarcher
  • Sepp Hochreiter

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been impressive success stories in mastering partially observable environments, mostly in the realm of computer games like Dota 2, StarCraft II, or MineCraft. However, existing methods lack interpretability in the sense that it is not comprehensible for humans what the agent stores in its memory. In this regard, we propose a novel memory mechanism that represents past events in human language. Our method uses CLIP to associate visual inputs with language tokens. Then we feed these tokens to a pretrained language model that serves the agent as memory and provides it with a coherent and human-readable representation of the past. We train our memory mechanism on a set of partially observable environments and find that it excels on tasks that require a memory component, while mostly attaining performance on-par with strong baselines on tasks that do not. On a challenging continuous recognition task, where memorizing the past is crucial, our memory mechanism converges two orders of magnitude faster than prior methods. Since our memory mechanism is human-readable, we can peek at an agent's memory and check whether crucial pieces of information have been stored. This significantly enhances troubleshooting and paves the way toward more interpretable agents.

PDF Details

NeurIPS Conference 2023 Conference Paper

Variational Annealing on Graphs for Combinatorial Optimization

  • Sebastian Sanokowski
  • Wilhelm Berghammer
  • Sepp Hochreiter
  • Sebastian Lehner

Several recent unsupervised learning methods use probabilistic approaches to solve combinatorial optimization (CO) problems based on the assumption of statistically independent solution variables. We demonstrate that this assumption imposes performance limitations in particular on difficult problem instances. Our results corroborate that an autoregressive approach which captures statistical dependencies among solution variables yields superior performance on many popular CO problems. We introduce Subgraph Tokenization in which the configuration of a set of solution variables is represented by a single token. This tokenization technique alleviates the drawback of the long sequential sampling procedure which is inherent to autoregressive methods without sacrificing expressivity. Importantly, we theoretically motivate an annealed entropy regularization and show empirically that it is essential for efficient and stable learning.

PDF Details

ICML Conference 2022 Conference Paper

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

  • Vihang Prakash Patil
  • Markus Hofmarcher
  • Marius-Constantin Dinu
  • Matthias Dorfer
  • Patrick M. Blies
  • Johannes Brandstetter
  • José Antonio Arjona-Medina
  • Sepp Hochreiter

Reinforcement learning algorithms require many samples when solving complex hierarchical tasks with sparse and delayed rewards. For such complex tasks, the recently proposed RUDDER uses reward redistribution to leverage steps in the Q-function that are associated with accomplishing sub-tasks. However, often only few episodes with high rewards are available as demonstrations since current exploration strategies cannot discover them in reasonable time. In this work, we introduce Align-RUDDER, which utilizes a profile model for reward redistribution that is obtained from multiple sequence alignment of demonstrations. Consequently, Align-RUDDER employs reward redistribution effectively and, thereby, drastically improves learning on few demonstrations. Align-RUDDER outperforms competitors on complex artificial tasks with delayed rewards and few demonstrations. On the Minecraft ObtainDiamond task, Align-RUDDER is able to mine a diamond, though not frequently. Code is available at github. com/ml-jku/align-rudder.

Details

NeurIPS Conference 2022 Conference Paper

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

  • Andreas Fürst
  • Elisabeth Rumetshofer
  • Johannes Lehner
  • Viet T. Tran
  • Fei Tang
  • Hubert Ramsauer
  • David Kreil
  • Michael Kopp

CLIP yielded impressive results on zero-shot transfer learning tasks and is considered as a foundation model like BERT or GPT3. CLIP vision models that have a rich representation are pre-trained using the InfoNCE objective and natural language supervision before they are fine-tuned on particular tasks. Though CLIP excels at zero-shot transfer learning, it suffers from an explaining away problem, that is, it focuses on one or few features, while neglecting other relevant features. This problem is caused by insufficiently extracting the covariance structure in the original multi-modal data. We suggest to use modern Hopfield networks to tackle the problem of explaining away. Their retrieved embeddings have an enriched covariance structure derived from co-occurrences of features in the stored embeddings. However, modern Hopfield networks increase the saturation effect of the InfoNCE objective which hampers learning. We propose to use the InfoLOOB objective to mitigate this saturation effect. We introduce the novel "Contrastive Leave One Out Boost" (CLOOB), which uses modern Hopfield networks for covariance enrichment together with the InfoLOOB objective. In experiments we compare CLOOB to CLIP after pre-training on the Conceptual Captions and the YFCC dataset with respect to their zero-shot transfer learning performance on other datasets. CLOOB consistently outperforms CLIP at zero-shot transfer learning across all considered architectures and datasets.

PDF Details

ICML Conference 2022 Conference Paper

History Compression via Language Models in Reinforcement Learning

  • Fabian Paischer
  • Thomas Adler
  • Vihang Prakash Patil
  • Angela Bitto-Nemling
  • Markus Holzleitner
  • Sebastian Lehner
  • Hamid Eghbal-Zadeh
  • Sepp Hochreiter

In a partially observable Markov decision process (POMDP), an agent typically uses a representation of the past to approximate the underlying MDP. We propose to utilize a frozen Pretrained Language Transformer (PLT) for history representation and compression to improve sample efficiency. To avoid training of the Transformer, we introduce FrozenHopfield, which automatically associates observations with pretrained token embeddings. To form these associations, a modern Hopfield network stores these token embeddings, which are retrieved by queries that are obtained by a random but fixed projection of observations. Our new method, HELM, enables actor-critic network architectures that contain a pretrained language Transformer for history representation as a memory module. Since a representation of the past need not be learned, HELM is much more sample efficient than competitors. On Minigrid and Procgen environments HELM achieves new state-of-the-art results. Our code is available at https: //github. com/ml-jku/helm.

Details

ICLR Conference 2021 Conference Paper

Hopfield Networks is All You Need

  • Hubert Ramsauer
  • Bernhard Schäfl
  • Johannes Lehner
  • Philipp Seidl
  • Michael Widrich
  • Lukas Gruber
  • Markus Holzleitner
  • Thomas Adler

We introduce a modern Hopfield network with continuous states and a corresponding update rule. The new Hopfield network can store exponentially (with the dimension of the associative space) many patterns, retrieves the pattern with one update, and has exponentially small retrieval errors. It has three types of energy minima (fixed points of the update): (1) global fixed point averaging over all patterns, (2) metastable states averaging over a subset of patterns, and (3) fixed points which store a single pattern. The new update rule is equivalent to the attention mechanism used in transformers. This equivalence enables a characterization of the heads of transformer models. These heads perform in the first layers preferably global averaging and in higher layers partial averaging via metastable states. The new modern Hopfield network can be integrated into deep learning architectures as layers to allow the storage of and access to raw input data, intermediate results, or learned prototypes. These Hopfield layers enable new ways of deep learning, beyond fully-connected, convolutional, or recurrent networks, and provide pooling, memory, association, and attention mechanisms. We demonstrate the broad applicability of the Hopfield layers across various domains. Hopfield layers improved state-of-the-art on three out of four considered multiple instance learning problems as well as on immune repertoire classification with several hundreds of thousands of instances. On the UCI benchmark collections of small classification tasks, where deep learning methods typically struggle, Hopfield layers yielded a new state-of-the-art when compared to different machine learning methods. Finally, Hopfield layers achieved state-of-the-art on two drug design datasets. The implementation is available at: \url{https://github.com/ml-jku/hopfield-layers}

Details

ICML Conference 2021 Conference Paper

MC-LSTM: Mass-Conserving LSTM

  • Pieter-Jan Hoedt
  • Frederik Kratzert
  • Daniel Klotz
  • Christina Halmich
  • Markus Holzleitner
  • Grey Nearing
  • Sepp Hochreiter
  • Günter Klambauer

The success of Convolutional Neural Networks (CNNs) in computer vision is mainly driven by their strong inductive bias, which is strong enough to allow CNNs to solve vision-related tasks with random weights, meaning without learning. Similarly, Long Short-Term Memory (LSTM) has a strong inductive bias towards storing information over time. However, many real-world systems are governed by conservation laws, which lead to the redistribution of particular quantities {—} e. g. in physical and economical systems. Our novel Mass-Conserving LSTM (MC-LSTM) adheres to these conservation laws by extending the inductive bias of LSTM to model the redistribution of those stored quantities. MC-LSTMs set a new state-of-the-art for neural arithmetic units at learning arithmetic operations, such as addition tasks, which have a strong conservation law, as the sum is constant over time. Further, MC-LSTM is applied to traffic forecasting, modeling a pendulum, and a large benchmark dataset in hydrology, where it sets a new state-of-the-art for predicting peak flows. In the hydrology example, we show that MC-LSTM states correlate with real world processes and are therefore interpretable.

Details

NeurIPS Conference 2020 Conference Paper

Modern Hopfield Networks and Attention for Immune Repertoire Classification

  • Michael Widrich
  • Bernhard Schäfl
  • Milena Pavlović
  • Hubert Ramsauer
  • Lukas Gruber
  • Markus Holzleitner
  • Johannes Brandstetter
  • Geir Kjetil Sandve

A central mechanism in machine learning is to identify, store, and recognize patterns. How to learn, access, and retrieve such patterns is crucial in Hopfield networks and the more recent transformer architectures. We show that the attention mechanism of transformer architectures is actually the update rule of modern Hopfield networks that can store exponentially many patterns. We exploit this high storage capacity of modern Hopfield networks to solve a challenging multiple instance learning (MIL) problem in computational biology: immune repertoire classification. In immune repertoire classification, a vast number of immune receptors are used to predict the immune status of an individual. This constitutes a MIL problem with an unprecedentedly massive number of instances, two orders of magnitude larger than currently considered problems, and with an extremely low witness rate. Accurate and interpretable machine learning methods solving this problem could pave the way towards new vaccines and therapies, which is currently a very relevant research topic intensified by the COVID-19 crisis. In this work, we present our novel method DeepRC that integrates transformer-like attention, or equivalently modern Hopfield networks, into deep learning architectures for massive MIL such as immune repertoire classification. We demonstrate that DeepRC outperforms all other methods with respect to predictive performance on large-scale experiments including simulated and real-world virus infection data and enables the extraction of sequence motifs that are connected to a given disease class. Source code and datasets: https: //github. com/ml-jku/DeepRC

PDF Details

NeurIPS Conference 2019 Conference Paper

RUDDER: Return Decomposition for Delayed Rewards

  • Jose A. Arjona-Medina
  • Michael Gillhofer
  • Michael Widrich
  • Thomas Unterthiner
  • Johannes Brandstetter
  • Sepp Hochreiter

We propose RUDDER, a novel reinforcement learning approach for delayed rewards in finite Markov decision processes (MDPs). In MDPs the Q-values are equal to the expected immediate reward plus the expected future rewards. The latter are related to bias problems in temporal difference (TD) learning and to high variance problems in Monte Carlo (MC) learning. Both problems are even more severe when rewards are delayed. RUDDER aims at making the expected future rewards zero, which simplifies Q-value estimation to computing the mean of the immediate reward. We propose the following two new concepts to push the expected future rewards toward zero. (i) Reward redistribution that leads to return-equivalent decision processes with the same optimal policies and, when optimal, zero expected future rewards. (ii) Return decomposition via contribution analysis which transforms the reinforcement learning task into a regression task at which deep learning excels. On artificial tasks with delayed rewards, RUDDER is significantly faster than MC and exponentially faster than Monte Carlo Tree Search (MCTS), TD(λ), and reward shaping approaches. At Atari games, RUDDER on top of a Proximal Policy Optimization (PPO) baseline improves the scores, which is most prominent at games with delayed rewards.

PDF Details

ICML Conference 2018 Conference Paper

First Order Generative Adversarial Networks

  • Calvin Seward
  • Thomas Unterthiner
  • Urs Bergmann
  • Nikolay Jetchev
  • Sepp Hochreiter

GANs excel at learning high dimensional distributions, but they can update generator parameters in directions that do not correspond to the steepest descent direction of the objective. Prominent examples of problematic update directions include those used in both Goodfellow’s original GAN and the WGAN-GP. To formally describe an optimal update direction, we introduce a theoretical framework which allows the derivation of requirements on both the divergence and corresponding method for determining an update direction, with these requirements guaranteeing unbiased mini-batch updates in the direction of steepest descent. We propose a novel divergence which approximates the Wasserstein distance while regularizing the critic’s first order information. Together with an accompanying update direction, this divergence fulfills the requirements for unbiased steepest descent updates. We verify our method, the First Order GAN, with image generation on CelebA, LSUN and CIFAR-10 and set a new state of the art on the One Billion Word language generation task.

Details

NeurIPS Conference 2017 Conference Paper

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

  • Martin Heusel
  • Hubert Ramsauer
  • Thomas Unterthiner
  • Bernhard Nessler
  • Sepp Hochreiter

Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved. We propose a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions. TTUR has an individual learning rate for both the discriminator and the generator. Using the theory of stochastic approximation, we prove that the TTUR converges under mild assumptions to a stationary local Nash equilibrium. The convergence carries over to the popular Adam optimization, for which we prove that it follows the dynamics of a heavy ball with friction and thus prefers flat minima in the objective landscape. For the evaluation of the performance of GANs at image generation, we introduce the `Fréchet Inception Distance'' (FID) which captures the similarity of generated images to real ones better than the Inception Score. In experiments, TTUR improves learning for DCGANs and Improved Wasserstein GANs (WGAN-GP) outperforming conventional GAN training on CelebA, CIFAR-10, SVHN, LSUN Bedrooms, and the One Billion Word Benchmark.

PDF Details

NeurIPS Conference 2017 Conference Paper

Self-Normalizing Neural Networks

  • Günter Klambauer
  • Thomas Unterthiner
  • Andreas Mayr
  • Sepp Hochreiter

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNNs) are rare. FNNs that perform well are typically shallow and, therefore cannot exploit many levels of abstract representations. We introduce self-normalizing neural networks (SNNs) to enable high-level abstract representations. While batch normalization requires explicit normalization, neuron activations of SNNs automatically converge towards zero mean and unit variance. The activation function of SNNs are "scaled exponential linear units" (SELUs), which induce self-normalizing properties. Using the Banach fixed-point theorem, we prove that activations close to zero mean and unit variance that are propagated through many network layers will converge towards zero mean and unit variance -- even under the presence of noise and perturbations. This convergence property of SNNs allows to (1) train deep networks with many layers, (2) employ strong regularization, and (3) to make learning highly robust. Furthermore, for activations not close to unit variance, we prove an upper and lower bound on the variance, thus, vanishing and exploding gradients are impossible. We compared SNNs on (a) 121 tasks from the UCI machine learning repository, on (b) drug discovery benchmarks, and on (c) astronomy tasks with standard FNNs and other machine learning methods such as random forests and support vector machines. For FNNs we considered (i) ReLU networks without normalization, (ii) batch normalization, (iii) layer normalization, (iv) weight normalization, (v) highway networks, (vi) residual networks. SNNs significantly outperformed all competing FNN methods at 121 UCI tasks, outperformed all competing methods at the Tox21 dataset, and set a new record at an astronomy data set. The winning SNN architectures are often very deep.

PDF Details

NeurIPS Conference 2015 Conference Paper

Rectified Factor Networks

  • Djork-Arné Clevert
  • Andreas Mayr
  • Thomas Unterthiner
  • Sepp Hochreiter

We propose rectified factor networks (RFNs) to efficiently construct very sparse, non-linear, high-dimensional representations of the input. RFN models identify rare and small events, have a low interference between code units, have a small reconstruction error, and explain the data covariance structure. RFN learning is a generalized alternating minimization algorithm derived from the posterior regularization method which enforces non-negative and normalized posterior means. We proof convergence and correctness of the RFN learning algorithm. On benchmarks, RFNs are compared to other unsupervised methods like autoencoders, RBMs, factor analysis, ICA, and PCA. In contrast to previous sparse coding methods, RFNs yield sparser codes, capture the data's covariance structure more precisely, and have a significantly smaller reconstruction error. We test RFNs as pretraining technique of deep networks on different vision datasets, where RFNs were superior to RBMs and autoencoders. On gene expression data from two pharmaceutical drug discovery studies, RFNs detected small and rare gene modules that revealed highly relevant new biological insights which were so far missed by other unsupervised methods. RFN package for GPU/CPU is available at http: //www. bioinf. jku. at/software/rfn.

PDF Details

NeurIPS Conference 2002 Conference Paper

Coulomb Classifiers: Generalizing Support Vector Machines via an Analogy to Electrostatic Systems

  • Sepp Hochreiter
  • Michael Mozer
  • Klaus Obermayer

We introduce a family of classiflers based on a physical analogy to an electrostatic system of charged conductors. The family, called Coulomb classiflers, includes the two best-known support-vector machines (SVMs), the ”{SVM and the C{SVM. In the electrostat- ics analogy, a training example corresponds to a charged conductor at a given location in space, the classiflcation function corresponds to the electrostatic potential function, and the training objective function corresponds to the Coulomb energy. The electrostatic framework provides not only a novel interpretation of existing algo- rithms and their interrelationships, but it suggests a variety of new methods for SVMs including kernels that bridge the gap between polynomial and radial-basis functions, objective functions that do not require positive-deflnite kernels, regularization techniques that allow for the construction of an optimal classifler in Minkowski space. Based on the framework, we propose novel SVMs and per- form simulation studies to show that they are comparable or su- perior to standard SVMs. The experiments include classiflcation tasks on data which are represented in terms of their pairwise prox- imities, where a Coulomb Classifler outperformed standard SVMs.

PDF Details

NeurIPS Conference 2002 Conference Paper

Feature Selection and Classification on Matrix Data: From Large Margins to Small Covering Numbers

  • Sepp Hochreiter
  • Klaus Obermayer

We investigate the problem of learning a classiflcation task for datasets which are described by matrices. Rows and columns of these matrices correspond to objects, where row and column ob- jects may belong to difierent sets, and the entries in the matrix express the relationships between them. We interpret the matrix el- ements as being produced by an unknown kernel which operates on object pairs and we show that - under mild assumptions - these ker- nels correspond to dot products in some (unknown) feature space. Minimizing a bound for the generalization error of a linear classi- fler which has been obtained using covering numbers we derive an objective function for model selection according to the principle of structural risk minimization. The new objective function has the advantage that it allows the analysis of matrices which are not pos- itive deflnite, and not even symmetric or square. We then consider the case that row objects are interpreted as features. We suggest an additional constraint, which imposes sparseness on the row objects and show, that the method can then be used for feature selection. Finally, we apply this method to data obtained from DNA microar- rays, where \column" objects correspond to samples, \row" objects correspond to genes and matrix elements correspond to expression levels. Benchmarks are conducted using standard one-gene classifl- cation and support vector machines and K-nearest neighbors after standard feature selection. Our new method extracts a sparse set of genes and provides superior classiflcation results.

PDF Details

NeurIPS Conference 2000 Conference Paper

Beyond Maximum Likelihood and Density Estimation: A Sample-Based Criterion for Unsupervised Learning of Complex Models

  • Sepp Hochreiter
  • Michael Mozer

The goal of many unsupervised learning procedures is to bring two probability distributions into alignment. Generative models such as Gaussian mixtures and Boltzmann machines can be cast in this light, as can recoding models such as ICA and projection pursuit. We propose a novel sample-based error measure for these classes of models, which applies even in situations where maximum likelihood (ML) and probability density estimation-based formulations can(cid: 173) not be applied, e. g. , models that are nonlinear or have intractable posteriors. Furthermore, our sample-based error measure avoids the difficulties of approximating a density function. We prove that with an unconstrained model, (1) our approach converges on the correct solution as the number of samples goes to infinity, and (2) the expected solution of our approach in the generative framework is the ML solution. Finally, we evaluate our approach via simula(cid: 173) tions of linear and nonlinear models on mixture of Gaussians and ICA problems. The experiments show the broad applicability and generality of our approach.

PDF Details

NeurIPS Conference 1998 Conference Paper

Source Separation as a By-Product of Regularization

  • Sepp Hochreiter
  • Jürgen Schmidhuber

This paper reveals a previously ignored connection between two important fields: regularization and independent component anal(cid: 173) ysis (ICA). We show that at least one representative of a broad class of algorithms (regularizers that reduce network complexity) extracts independent features as a by-product. This algorithm is Flat Minimum Search (FMS), a recent general method for finding low-complexity networks with high generalization capability. FMS works by minimizing both training error and required weight pre(cid: 173) cision. According to our theoretical analysis the hidden layer of an FMS-trained autoassociator attempts at coding each input by a sparse code with as few simple features as possible. In experi(cid: 173) ments the method extracts optimal codes for difficult versions of the "noisy bars" benchmark problem by separating the underlying sources, whereas ICA and PCA fail. Real world images are coded with fewer bits per pixel than by ICA or PCA.

PDF Details

NeurIPS Conference 1996 Conference Paper

LSTM can Solve Hard Long Time Lag Problems

  • Sepp Hochreiter
  • Jürgen Schmidhuber

Standard recurrent nets cannot deal with long minimal time lags between relevant signals. Several recent NIPS papers propose alter(cid: 173) native methods. We first show: problems used to promote various previous algorithms can be solved more quickly by random weight guessing than by the proposed algorithms. We then use LSTM, our own recent algorithm, to solve a hard problem that can neither be quickly solved by random search nor by any other recurrent net algorithm we are aware of. 1 TRIVIAL PREVIOUS LONG TIME LAG PROBLEMS Traditional recurrent nets fail in case 'of long minimal time lags between input sig(cid: 173) nals and corresponding error signals [7, 3]. Many recent papers propose alternative methods, e. g. , [16, 12, 1, 5, 9]. For instance, Bengio et ale investigate methods such as simulated annealing, multi-grid random search, time-weighted pseudo-Newton optimization, and discrete error propagation [3]. They also propose. an EM ap(cid: 173) proach [1]. Quite a few papers use variants of the "2-sequence problem" (and ('latch problem" ) to show the proposed algorithm's superiority, e. g. [3, 1, 5, 9]. Some pa(cid: 173) pers also use the "parity problem", e. g. , [3, 1]. Some of Tomita's [18] grammars are also often used as benchmark problems for recurrent nets [2, 19, 14, 11]. Trivial versus non-trivial tasks. By our definition, a "trivial" task is one that can be solved quickly by random search (RS) in weight space. RS works as follows: REPEAT randomly initialize the weights and test the resulting net on a training set UNTIL solution found.

PDF Details

NeurIPS Conference 1994 Conference Paper

SIMPLIFYING NEURAL NETS BY DISCOVERING FLAT MINIMA

  • Sepp Hochreiter
  • Jürgen Schmidhuber

We present a new algorithm for finding low complexity networks with high generalization capability. The algorithm searches for large connected regions of so-called ''fiat'' minima of the error func(cid: 173) tion. In the weight-space environment of a "flat" minimum, the error remains approximately constant. Using an MDL-based ar(cid: 173) gument, flat minima can be shown to correspond to low expected overfitting. Although our algorithm requires the computation of second order derivatives, it has backprop's order of complexity. Experiments with feedforward and recurrent nets are described. In an application to stock market prediction, the method outperforms conventional backprop, weight decay, and "optimal brain surgeon".

PDF Details
v2026.09.13