Pascal Vincent

Compositional Risk Minimization

Charles Arnal

Compositional generalization is a crucial step towards developing data-efficient intelligent machines that generalize in human-like ways. In… (voir plus) this work, we tackle a challenging form of distribution shift, termed compositional shift, where some attribute combinations are completely absent at training but present in the test distribution. This shift tests the model's ability to generalize compositionally to novel attribute combinations in discriminative tasks. We model the data with flexible additive energy distributions, where each energy term represents an attribute, and derive a simple alternative to empirical risk minimization termed compositional risk minimization (CRM). We first train an additive energy classifier to predict the multiple attributes and then adjust this classifier to tackle compositional shifts. We provide an extensive theoretical analysis of CRM, where we show that our proposal extrapolates to special affine hulls of seen attribute combinations. Empirical evaluations on benchmark datasets confirms the improved robustness of CRM compared to other methods from the literature designed to tackle various forms of subpopulation shifts.

2025-10-05

Proceedings of the 42nd International Conference on Machine Learning (publié)

doi.org

proceedings.mlr.press

MaestroMotif: Skill Design From Artificial Intelligence Feedback

Martin Klissarov

Mikael Henaff

Roberta Raileanu

Marlos C. Machado

Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an… (voir plus) AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.

2025-04-22

International Conference on Learning Representations (Accept (Oral))

doi.org

openreview.net

The Pitfalls of Memorization: When Memorization Hurts Generalization

Reza Bayat

Mohammad Pezeshki

Elvis Dohmatob

David Lopez-Paz

Pascal Vincent

Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explan… (voir plus)ations.This behavior leads to poor generalization when the learned explanations rely on spurious correlations. In this work, we formalize the interplay between memorization and generalization, showing that spurious correlations would particularly lead to poor generalization when are combined with memorization. Memorization can reduce training loss to zero, leaving no incentive to learn robust, generalizable patterns. To address this, we propose memorization-aware training (MAT), which uses held-out predictions as a signal of memorization to shift a model's logits. MAT encourages learning robust patterns invariant across distributions, improving generalization under distribution shifts.

2025-04-22

International Conference on Learning Representations (Accept (Poster))

doi.org

openreview.net

Motif: Intrinsic Motivation From Artificial Intelligence Feedback

Roberta Raileanu

Mikael Henaff

Exploring rich environments and evaluating one's actions without prior knowledge is immensely challenging. In this paper, we propose Motif, … (voir plus)a general method to interface such prior knowledge from a Large Language Model (LLM) with an agent. Motif is based on the idea of grounding LLMs for decision-making without requiring them to interact with the environment: it elicits preferences from an LLM over pairs of captions to construct an intrinsic reward, which is then used to train agents with reinforcement learning. We evaluate Motif's performance and behavior on the challenging, open-ended and procedurally-generated NetHack game. Surprisingly, by only learning to maximize its intrinsic reward, Motif achieves a higher game score than an algorithm directly trained to maximize the score itself. When combining Motif's intrinsic reward with the environment reward, our method significantly outperforms existing approaches and makes progress on tasks where no advancements have ever been made without demonstrations. Finally, we show that Motif mostly generates intuitive human-aligned behaviors which can be steered easily through prompt modifications, while scaling well with the LLM size and the amount of information given in the prompt.

2024-05-06

International Conference on Learning Representations (Accept (poster))

doi.org

openreview.net

On the Identifiability of Quantized Factors

Vitória Barin-Pacela

Kartik Ahuja

Simon Lacoste-Julien

Pascal Vincent

Disentanglement aims to recover meaningful latent ground-truth factors from the observed distribution solely, and is formalized through the … (voir plus)theory of identifiability. The identifiability of independent latent factors is proven to be impossible in the unsupervised i.i.d. setting under a general nonlinear map from factors to observations. In this work, however, we demonstrate that it is possible to recover quantized latent factors under a generic nonlinear diffeomorphism. We only assume that the latent factors have independent discontinuities in their density, without requiring the factors to be statistically independent. We introduce this novel form of identifiability, termed quantized factor identifiability, and provide a comprehensive proof of the recovery of the quantized factors.

2023-12-31

Conference on Causal Learning and Reasoning (publié)

doi.org

proceedings.mlr.press

PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning

Florian Bordes

Shashank Shekhar

Mark Ibrahim

Diane Bouchacourt

Pascal Vincent

Ari S. Morcos

Synthetic image datasets offer unmatched advantages for designing and evaluating deep neural networks: they make it possible to (i) render a… (voir plus)s many data samples as needed, (ii) precisely control each scene and yield granular ground truth labels (and captions), (iii) precisely control distribution shifts between training and testing to isolate variables of interest for sound experimentation.Despite such promise, the use of synthetic image data is still limited -- and often played down -- mainly due to their lack of realism. Most works therefore rely on datasets of real images, which have often been scraped from public images on the internet, and may have issues with regards to privacy, bias, and copyright, while offering little control over how objects precisely appear.In this work, we present a path to democratize the use of photorealistic synthetic data: we develop a new generation of interactive environments for representation learning research, that offer both controllability and realism. We use the Unreal Engine, a powerful game engine well known in the entertainment industry, to produce PUG (Photorealistic Unreal Graphics) environments and datasets for representation learning. Using PUG for evaluation and fine-tuning, we demonstrate the potential of PUG to both enable more rigorous evaluations and to improve model training.

2023-12-11

Conference on Neural Information Processing Systems (Accept (Poster))

doi.org

openreview.net

Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning

Casey Meehan

Florian Bordes

Pascal Vincent

Kamalika Chaudhuri

Chuan Guo

Self-supervised learning (SSL) algorithms can produce useful image representations by learning to associate different parts of natural image… (voir plus)s with one another. However, when taken to the extreme, SSL models can unintendedly memorize specific parts in individual training samples rather than learning semantically meaningful associations. In this work, we perform a systematic study of the unintended memorization of image-specific information in SSL models -- which we refer to as déjà vu memorization. Concretely, we show that given the trained model and a crop of a training image containing only the background (e.g., water, sky, grass), it is possible to infer the foreground object with high accuracy or even visually reconstruct it. Furthermore, we show that déjà vu memorization is common to different SSL algorithms, is exacerbated by certain design choices, and cannot be detected by conventional techniques for evaluating representation quality. Our study of déjà vu memorization reveals previously unknown privacy risks in SSL models, as well as suggests potential practical mitigation strategies.

2023-12-11

Conference on Neural Information Processing Systems (Accept (poster))

doi.org

openreview.net

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Mahmoud Assran

Quentin Duval

Ishan Misra

Piotr Bojanowski

This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. W… (voir plus)e introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative approach for self-supervised learning from images. The idea behind I-JEPA is simple: from a single context block, predict the representations of various target blocks in the same image. A core design choice to guide I-JEPA towards producing semantic representations is the masking strategy; specifically, it is crucial to (a) sample target blocks with sufficiently large scale (semantic), and to (b) use a sufficiently informative (spatially distributed) context block. Empirically, when combined with Vision Transformers, we find I-JEPA to be highly scalable. For instance, we train a ViT-Huge/14 on ImageNet using 16 A100 GPUs in under 72 hours to achieve strong downstream performance across a wide range of tasks, from linear classification to object counting and depth prediction.

2023-06-16

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (publié)

doi.org

arxiv.org

The Emergence of Argument Structure in Artificial Languages

Tom Bosc

Pascal Vincent

Computational approaches to the study of language emergence can help us understand how natural languages are shaped by cognitive and sociocu… (voir plus)ltural factors. Previous work focused on tasks where agents refer to a single entity. In contrast, we study how agents predicate, that is, how they express that some relation holds between several entities. We introduce a setup where agents talk about a variable number of entities that can be partially observed by the listener. In the presence of a least-effort pressure, they tend to discuss only entities that are not observed by the listener. Thus we can obtain artificial phrases that denote a single entity, as well as artificial sentences that denote several entities. In natural languages, if we ignore the verb, phrases are usually concatenated, either in a specific order or by adding case markers to form sentences. Our setup allows us to quantify how much this holds in emergent languages using a metric we call concatenability. We also measure transitivity, which quantifies the importance of word order. We demonstrate the usefulness of this new setup and metrics for studying factors that influence argument structure. We compare agents having access to input representations structured into pre-segmented objects with properties, versus unstructured representations. Our results indicate that the awareness of object structure yields a more natural sentence organization.

2022-11-30

Transactions of the Association for Computational Linguistics (publié)

doi.org

Online Adversarial Attacks

Avishek Joey Bose

William L. Hamilton

Adversarial attacks expose important vulnerabilities of deep learning models, yet little attention has been paid to settings where data arri… (voir plus)ves as a stream. In this paper, we formalize the online adversarial attack problem, emphasizing two key elements found in real-world use-cases: attackers must operate under partial knowledge of the target model, and the decisions made by the attacker are irrevocable since they operate on a transient data stream. We first rigorously analyze a deterministic variant of the online threat model by drawing parallels to the well-studied

2022-04-24

International Conference on Learning Representations (Accept (Poster))

doi.org

openreview.net

Accounting for Variance in Machine Learning Benchmarks

Mirko Bronzi

Naz Sepah

Edward Raff

Kanika Madan

Vikram Voleti

Samira Ebrahimi Kahou

Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the l… (voir plus)earning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization, and hyperparameters choices. This is prohibitively expensive, and corners are cut to reach conclusions. We model the whole benchmarking process, revealing that variance due to data sampling, parameter initialization and hyperparameter choice impact markedly the results. We analyze the predominant comparison methods used today in the light of this variance. We show a counter-intuitive result that adding more sources of variation to an imperfect estimator approaches better the ideal estimator at a 51 times reduction in compute cost. Building on these results, we study the error rate of detecting improvements, on five different deep-learning tasks/architectures. This study leads us to propose recommendations for performance comparisons.

2021-04-05

Conference on Machine Learning and Systems (Accept)

doi.org

arxiv.org

Implicit Regularization via Neural Feature Alignment

R Devon Hjelm

We approach the problem of implicit regularization in deep learning from a geometrical viewpoint. We highlight a regularization effect induc… (voir plus)ed by a dynamical alignment of the neural tangent features introduced by Jacot et al, along a small number of task-relevant directions. This can be interpreted as a combined mechanism of feature selection and compression. By extrapolating a new analysis of Rademacher complexity bounds for linear models, we motivate and study a heuristic complexity measure that captures this phenomenon, in terms of sequences of tangent kernel classes along optimization paths.

2021-03-17

International Conference on Artificial Intelligence and Statistics (inconnu)

doi.org

proceedings.mlr.press

Communauté de pratique de Mila : L'IA agentique

Formation d'entrepreneurs scientifiques

Demandes de supervision

Pascal Vincent

Publications

Communauté de pratique de Mila : L'IA agentique

Formation d'entrepreneurs scientifiques

Demandes de supervision

Mots-clés populaires:

Pascal Vincent

Publications