Publications

Stochastic positional embeddings improve masked image modeling
Amir Bar
Florian Bordes
Assaf Shocher
Mahmoud Assran
P Vincent
Nicolas Ballas
Trevor Darrell
Amir Globerson
Yann Lecun
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
Jesse Farebrother
Jordi Orbay
Quan Vuong
Adrien Ali Taiga
Yevgen Chebotar
Ted Xiao
Alex Irpan
Sergey Levine
Pablo Samuel Castro
Aleksandra Faust
Aviral Kumar
Rishabh Agarwal
Value functions are a central component of deep reinforcement learning (RL). These functions, parameterized by neural networks, are trained … (voir plus)using a mean squared error regression objective to match bootstrapped target values. However, scaling value-based RL methods that use regression to large networks, such as high-capacity Transformers, has proven challenging. This difficulty is in stark contrast to supervised learning: by leveraging a cross-entropy classification loss, supervised methods have scaled reliably to massive networks. Observing this discrepancy, in this paper, we investigate whether the scalability of deep RL can also be improved simply by using classification in place of regression for training value functions. We demonstrate that value functions trained with categorical cross-entropy significantly improves performance and scalability in a variety of domains. These include: single-task RL on Atari 2600 games with SoftMoEs, multi-task RL on Atari with large-scale ResNets, robotic manipulation with Q-transformers, playing Chess without search, and a language-agent Wordle task with high-capacity Transformers, achieving state-of-the-art results on these domains. Through careful analysis, we show that the benefits of categorical cross-entropy primarily stem from its ability to mitigate issues inherent to value-based RL, such as noisy targets and non-stationarity. Overall, we argue that a simple shift to training value functions with categorical cross-entropy can yield substantial improvements in the scalability of deep RL at little-to-no cost.
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
A Tale of Tails: Model Collapse as a Change of Scaling Laws
Elvis Dopgima Dohmatob
Yunzhen Feng
Pu Yang
Francois Charton
Julia Kempe
As AI model size grows, neural scaling laws have become a crucial tool to predict the improvements of large models when increasing … (voir plus)capacity and the size of original (human or natural) training data. Yet, the widespread use of popular models means that the ecosystem of online data and text will co-evolve to progressively contain increased amounts of synthesized data. In this paper we ask: How will the scaling laws change in the inevitable regime where synthetic data makes its way into the training corpus? Will future models, still improve, or be doomed to degenerate up to total (model) collapse? We develop a theoretical framework of model collapse through the lens of scaling laws. We discover a wide range of decay phenomena, analyzing loss of scaling, shifted scaling with number of generations, the ”un-learning" of skills, and grokking when mixing human and synthesized data. Our theory is validated by large-scale experiments with a transformer on an arithmetic task and text generation using the large language model Llama2.
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
Ziquan Liu
Yufei Cui
Yan Yan
Yi Xu
Xiangyang Ji
Xue Liu
Antoni B. Chan
In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient healt… (voir plus)h and road safety, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks and reliable uncertainty quantification in decision-making. With extensive research focused on enhancing adversarial robustness through various forms of adversarial training (AT), a notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. To address this gap, this study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks within the adversarial defense community. It is first unveiled that existing CP methods do not produce informative prediction sets under the commonly used
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
Think Before You Act: Decision Transformers with Working Memory
Jikun Kang
Romain Laroche
Xingdi Yuan
Adam Trischler
Xue Liu
Jie Fu
Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance rel… (voir plus)ies on massive data and computation. We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training. As a result, training on a new task may deteriorate the model's performance on previous tasks. In contrast to LLMs' implicit memory mechanism, the human brain utilizes distributed memory storage, which helps manage and organize multiple skills efficiently, mitigating the forgetting phenomenon. Inspired by this, we propose a working memory module to store, blend, and retrieve information for different downstream tasks. Evaluation results show that the proposed method improves training efficiency and generalization in Atari games and Meta-World object manipulation tasks. Moreover, we demonstrate that memory fine-tuning further enhances the adaptability of the proposed architecture.
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Do Transformer World Models Give Better Policy Gradients?
Michel Ma
Tianwei Ni
Clement Gehring
Pierluca D'Oro
Pierre-Luc Bacon
A natural approach for reinforcement learning is to predict future rewards by unrolling a neural network world model, and to backpropagate t… (voir plus)hrough the resulting computational graph to learn a policy. However, this method often becomes impractical for long horizons since typical world models induce hard-to-optimize loss landscapes. Transformers are known to efficiently propagate gradients over long horizons: could they be the solution to this problem? Surprisingly, we show that commonly-used transformer world models produce circuitous gradient paths, which can be detrimental to long-range policy gradients. To tackle this challenge, we propose a class of world models called Actions World Models (AWMs), designed to provide more direct routes for gradient propagation. We integrate such AWMs into a policy gradient framework that underscores the relationship between network architectures and the policy gradient updates they inherently represent. We demonstrate that AWMs can generate optimization landscapes that are easier to navigate even when compared to those from the simulator itself. This property allows transformer AWMs to produce better policies than competitive baselines in realistic long-horizon tasks.
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
Antonio Orvieto
Soham De
Caglar Gulçehre
Razvan Pascanu
Samuel L. Smith
Deep neural networks based on linear RNNs interleaved with position-wise MLPs are gaining traction as competitive approaches for sequence mo… (voir plus)deling. Examples of such architectures include state-space models (SSMs) like S4, LRU, and Mamba: recently proposed models that achieve promising performance on text, genetics, and other data that require long-range reasoning. Despite experimental evidence highlighting these architectures’ effectiveness and computational efficiency, their expressive power remains relatively unexplored, especially in connection to specific choices crucial in practice - e.g., carefully designed initialization distribution and potential use of complex numbers. In this paper, we show that combining MLPs with both real or complex linear diagonal recurrences leads to arbitrarily precise approximation of regular causal sequence-to-sequence maps. At the heart of our proof, we rely on a separation of concerns: the linear RNN provides a lossless encoding of the input sequence, and the MLP performs non-linear processing on this encoding. While we show that real diagonal linear recurrences are enough to achieve universality in this architecture, we prove that employing complex eigenvalues near unit disk - i.e., empirically the most successful strategy in S4 - greatly helps the RNN in storing information. We connect this finding with the vanishing gradient issue and provide experiments supporting our claims.
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
Unsupervised Concept Discovery Mitigates Spurious Correlations
Md Rifat Arefin
Yan Zhang
Aristide Baratin
Francesco Locatello
Irina Rish
Dianbo Liu
Kenji Kawaguchi
Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases. Addressing this ch… (voir plus)allenge typically involves methods relying on prior knowledge and group annotation to remove spurious correlations, which may not be readily available in many applications. In this paper, we establish a novel connection between unsupervised object-centric learning and mitigation of spurious correlations. Instead of directly inferring subgroups with varying correlations with labels, our approach focuses on discovering concepts: discrete ideas that are shared across input samples. Leveraging existing object-centric representation learning, we introduce CoBalT: a concept balancing technique that effectively mitigates spurious correlations without requiring human labeling of subgroups. Evaluation across the benchmark datasets for sub-population shifts demonstrate superior or competitive performance compared state-of-the-art baselines, without the need for group annotation. Code is available at https://github.com/rarefin/CoBalT.
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
When is Transfer Learning Possible?
My Phan
Kianté Brantley
Stephanie Milani
Soroush Mehri
Gokul Swamy
Geoff Gordon
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
Alexandre Drouin
Maxime Gasse
Massimo Caccia
Issam H. Laradji
Manuel Del Verme
Tom Marty
Léo Boisvert
Megh Thakkar
Quentin Cappart
David Vázquez
Nicolas Chapados
Alexandre Lacoste
We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuri… (voir plus)ng the agents' ability to perform tasks that span the typical daily work of knowledge workers utilizing enterprise software systems. To this end, we propose WorkArena, a remote-hosted benchmark of 33 tasks based on the widely-used ServiceNow platform. We also introduce BrowserGym, an environment for the design and evaluation of such agents, offering a rich set of actions as well as multimodal observations. Our empirical evaluation reveals that while current agents show promise on WorkArena, there remains a considerable gap towards achieving full task automation. Notably, our analysis uncovers a significant performance disparity between open and closed-source LLMs, highlighting a critical area for future exploration and development in the field.
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Charles Guille-escuret
Hiroki Naganuma
Kilian Fatras
Ioannis Mitliagkas
Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice. Stochastic first-or… (voir plus)der optimization algorithms are known to efficiently locate favorable minima in deep neural networks. This efficiency, however, contrasts with the non-convex and seemingly complex structure of neural loss landscapes. In this study, we delve into the fundamental geometric properties of sampled gradients along optimization paths. We focus on two key quantities, which appear in the restricted secant inequality and error bound. Both hold high significance for first-order optimization. Our analysis reveals that these quantities exhibit predictable, consistent behavior throughout training, despite the stochasticity induced by sampling minibatches. Our findings suggest that not only do optimization trajectories never encounter significant obstacles, but they also maintain stable dynamics during the majority of training. These observed properties are sufficiently expressive to theoretically guarantee linear convergence and prescribe learning rate schedules mirroring empirical practices. We conduct our experiments on image classification, semantic segmentation and language modeling across different batch sizes, network architectures, datasets, optimizers, and initialization seeds. We discuss the impact of each factor. Our work provides novel insights into the properties of neural network loss functions, and opens the door to theoretical frameworks more relevant to prevalent practice.
2024-07-07
Proceedings of the 41st International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Prospective Messaging: Learning in Networks with Communication Delays
Ryan Fayyazi
Christian Dietrich Weilbach
Frank N. Wood
Inter-neuron communication delays are ubiquitous in physically realized neural networks such as biological neural circuits and neuromorphic … (voir plus)hardware. These delays have significant and often disruptive consequences on network dynamics during training and inference. It is therefore essential that communication delays be accounted for, both in computational models of biological neural networks and in large-scale neuromorphic systems. Nonetheless, communication delays have yet to be comprehensively addressed in either domain. In this paper, we first show that delays prevent state-of-the-art continuous-time neural networks called Latent Equilibrium (LE) networks from learning even simple tasks despite significant overparameterization. We then propose to compensate for communication delays by predicting future signals based on currently available ones. This conceptually straightforward approach, which we call prospective messaging (PM), uses only neuron-local information, and is flexible in terms of memory and computation requirements. We demonstrate that incorporating PM into delayed LE networks prevents reaction lags, and facilitates successful learning on Fourier synthesis and autoregressive video prediction tasks.
2024-07-06
ArXiv (prépublication)
doi.org
arxiv.org