Portrait of Emmanuel Bengio

Emmanuel Bengio

Associate Industry Member
Staff Machine Learning Scientist, Recursion
Research Topics
Deep Learning
Generative Models
GFlowNets
Molecular Modeling
Reinforcement Learning

Biography

Emmanuel Bengio is an ML Scientist at Valence Labs/Recursion, working on the intersection of GFlowNets and drug discovery. He did his PhD under Joelle Pineau and Doina Precup at McGill/Mila - Quebec Artificial Intelligence Institute, focusing on understanding generalization in deep RL.

Publications

GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
Correcting Momentum in Temporal Difference Learning
Emmanuel Bengio
Joelle Pineau
Doina Precup
A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, r… (see more)eapplying them at each iteration. We argue that, unlike in supervised learning, momentum in Temporal Difference (TD) learning accumulates gradients that become doubly stale: not only does the gradient of the loss change due to parameter updates, the loss itself changes due to bootstrapping. We first show that this phenomenon exists, and then propose a first-order correction term to momentum. We show that this correction term improves sample efficiency in policy evaluation by correcting target value drift. An important insight of this work is that deep RL methods are not always best served by directly importing techniques from the supervised setting.
2021-06-07
ArXiv (preprint)
openreview.net
openreview.net
Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
Emmanuel Bengio
Moksh J. Jain
Maksym Korablyov
Doina Precup
Yoshua Bengio
This paper is about the problem of learning a stochastic policy for generating an object (like a molecular graph) from a sequence of actions… (see more), such that the probability of generating an object is proportional to a given positive reward for that object. Whereas standard return maximization tends to converge to a single return-maximizing sequence, there are cases where we would like to sample a diverse set of high-return solutions. These arise, for example, in black-box function optimization when few rounds are possible, each with large batches of queries, where the batches should be diverse, e.g., in the design of new molecules. One can also see this as a problem of approximately converting an energy function to a generative distribution. While MCMC methods can achieve that, they are expensive and generally only perform local exploration. Instead, training a generative policy amortizes the cost of search during training and yields to fast generation. Using insights from Temporal Difference learning, we propose GFlowNet, based on a view of the generative process as a flow network, making it possible to handle the tricky case where different trajectories can yield the same final state, e.g., there are many ways to sequentially add atoms to generate some molecular graph. We cast the set of trajectories as a flow and convert the flow consistency equations into a learning objective, akin to the casting of the Bellman equations into Temporal Difference methods. We prove that any global minimum of the proposed objectives yields a policy which samples from the desired distribution, and demonstrate the improved performance and diversity of GFlowNet on a simple domain where there are many modes to the reward function, and on a molecule synthesis task.
openreview.net
Interference and Generalization in Temporal Difference Learning
Emmanuel Bengio
Joelle Pineau
Doina Precup
We study the link between generalization and interference in temporal-difference (TD) learning. Interference is defined as the inner product… (see more) of two different gradients, representing their alignment. This quantity emerges as being of interest from a variety of observations about neural networks, parameter sharing and the dynamics of learning. We find that TD easily leads to low-interference, under-generalizing parameters, while the effect seems reversed in supervised learning. We hypothesize that the cause can be traced back to the interplay between the dynamics of interference and bootstrapping. This is supported empirically by several observations: the negative relationship between the generalization gap and interference in TD, the negative effect of bootstrapping on interference and the local coherence of targets, and the contrast between the propagation rate of information in TD(0) versus TD(
2020-11-21
Proceedings of the 37th International Conference on Machine Learning (published)
proceedings.mlr.press
arxiv.org
World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions
Teng Long
Emmanuel Bengio
Ryan Lowe
Jackie Cheung
Doina Precup
Humans interpret texts with respect to some background information, or world knowledge, and we would like to develop automatic reading compr… (see more)ehension systems that can do the same. In this paper, we introduce a task and several models to drive progress towards this goal. In particular, we propose the task of rare entity prediction: given a web document with several entities removed, models are tasked with predicting the correct missing entities conditioned on the document context and the lexical resources. This task is challenging due to the diversity of language styles and the extremely large number of rare entities. We propose two recurrent neural network architectures which make use of external knowledge in the form of entity descriptions. Our experiments show that our hierarchical LSTM model performs significantly better at the rare entity prediction task than those that do not make use of external resources.
2017-09-01
Conference on Empirical Methods in Natural Language Processing (published)
doi.org
A Closer Look at Memorization in Deep Networks
Devansh Arpit
Stanisław Jastrzębski
Nicolas Ballas
David Scott Krueger
Emmanuel Bengio
Maxinder S. Kanwal
Tegan Maharaj
Asja Fischer
Aaron Courville
Yoshua Bengio
Simon Lacoste-Julien
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While dee… (see more)p networks are capable of memorizing noise data, our results suggest that they tend to prioritize learning simple patterns first. In our experiments, we expose qualitative differences in gradient-based optimization of deep neural networks (DNNs) on noise vs. real data. We also demonstrate that for appropriately tuned explicit regularization (e.g., dropout) we can degrade DNN training performance on noise datasets without compromising generalization on real data. Our analysis suggests that the notions of effective capacity which are dataset independent are unlikely to explain the generalization performance of deep networks when trained with gradient based methods because training data itself plays an important role in determining the degree of memorization.
2017-07-17
Proceedings of the 34th International Conference on Machine Learning (published)
proceedings.mlr.press
arxiv.org
Deep Nets Don't Learn via Memorization
David Scott Krueger
Nicolas Ballas
Stanisław Jastrzębski
Devansh Arpit
Maxinder S. Kanwal
Tegan Maharaj
Emmanuel Bengio
Asja Fischer
Aaron Courville
We use empirical methods to argue that deep neural networks (DNNs) do not achieve their performance by memorizing training data in spite of … (see more)overlyexpressive model architectures. Instead, they learn a simple available hypothesis that fits the finite data samples. In support of this view, we establish that there are qualitative differences when learning noise vs. natural datasets, showing: (1) more capacity is needed to fit noise, (2) time to convergence is longer for random labels, but shorter for random inputs, and (3) that DNNs trained on real data examples learn simpler functions than when trained with noise data, as measured by the sharpness of the loss function at convergence. Finally, we demonstrate that for appropriately tuned explicit regularization, e.g. dropout, we can degrade DNN training performance on noise datasets without compromising generalization on real data.
2017-02-17
International Conference on Learning Representations (published)
dblp.uni-trier.de