Laurent Charlin

Biographie

Laurent Charlin est titulaire d’une chaire en IA Canada-CIFAR et professeur agrégé à HEC Montréal. Il est également membre académique principal à Mila – Institut québécois d’intelligence artificielle.

Ses recherches portent sur le développement de nouveaux modèles d'apprentissage automatique pour aider à la prise de décision. Ses travaux récents concernent l'apprentissage à partir de données qui évoluent dans le temps. Il travaille également sur des applications dans des domaines tels que les systèmes de recommandation et l'optimisation.

Il est l'auteur de publications très citées sur les systèmes de dialogue (chatbots). Laurent Charlin a codéveloppé le Toronto Paper Matching System (TPMS), qui a été largement utilisé dans les conférences d'informatique pour faire correspondre les réviseur·euse·s aux articles. Il a également contribué à plusieurs MOOC récents, et a donné des conférences d'introduction et des interviews dans les médias pour contribuer au transfert de connaissances et améliorer la culture de l'IA.

Étudiants actuels

Neda Adl

Maîtrise recherche - HEC

Neda@mila.quebec

Anirudh Buvanesh

Doctorat - UdeM

Co-superviseur⋅e :

Aaron Courville

anirudb1102@gmail.com

felix.gauthier@mila.quebec

Félix Gauthier

Maîtrise recherche - HEC

Soraya Ghassemlou

Maîtrise recherche - McGill

soraya.ghassemlou@mila.quebec

Site web

nicolas.goulet@mila.quebec

Nicolas Goulet

Doctorat - HEC

Superviseur⋅e principal⋅e :

Eva Portelance

shubham.gupta@mila.quebec

Shubham Gupta

Doctorat - Université Laval

Superviseur⋅e principal⋅e :

Cem Subakan

Ben Hudson

Doctorat - UdeM

Co-superviseur⋅e :

Emma Frejinger

ben.hudson@mila.quebec

Site web

mizu.nishikawa-toomey@mila.quebec

Mizu Nishikawa-Toomey

Doctorat - UdeM

Co-superviseur⋅e :

Dhanya Sridhar

Doctorat - Concordia

Superviseur⋅e principal⋅e :

Mirco Ravanelli

firat.oncel@mila.quebec

Collaborateur·rice alumni - UdeM

ostapeno@mila.quebec

emiliano.penaloza@mila.quebec

Emiliano Penaloza

Doctorat - UdeM

Site web

omar.salemohamed@mila.quebec

Gaurav Sahu

Postdoctorat - HEC

Co-superviseur⋅e :

Chris Pal

gaurav.sahu@mila.quebec

Doctorat - UdeM

Yipeng Zhang

Doctorat - UdeM

yipeng.zhang@mila.quebec

Publications

Comparative Study of Learning Outcomes for Online Learning Platforms

Francois St-Hilaire

Nathan J. Burns

Robert Belfer

Muhammad Shayan

Ariella Smofsky

Dung D. Vu

Antoine Frau

Joseph Potochny

Farid Faraji

Vincent Pavero

Neroli Ko

Ansona Onyi Ching

Sabina Elkins

A. Stepanyan

Adela Matajova

Yoshua Bengio

Iulian V. Serban

Ekaterina Kochmar

2021-06-11

Lecture Notes in Computer Science (publié)

Pretraining Reward-Free Representations for Data-Efficient Reinforcement Learning

Philip Bachman

2021-03-08

International Conference on Learning Representations (inconnu)

Continual Learning via Local Module Composition

Oleksiy Ostapenko

Pau Rodríguez

Massimo Caccia

Modularity is a compelling solution to continual learning (CL), the problem of modeling sequences of related tasks. Learning and then compos… (voir plus)ing modules to solve different tasks provides an abstraction to address the principal challenges of CL including catastrophic forgetting, backward and forward transfer across tasks, and sub-linear model growth. We introduce local module composition (LMC), an approach to modular CL where each module is provided a local structural component that estimates a module's relevance to the input. Dynamic module composition is performed layer-wise based on local relevance scores. We demonstrate that agnosticity to task identities (IDs) arises from (local) structural learning that is module-specific as opposed to the task- and/or model-specific as in previous works, making LMC applicable to more CL settings compared to previous works. In addition, LMC also tracks statistics about the input distribution and adds new modules when outlier samples are detected. In the first set of experiments, LMC performs favorably compared to existing methods on the recent Continual Transfer-learning Benchmark without requiring task identities. In another study, we show that the locality of structural learning allows LMC to interpolate to related but unseen tasks (OOD), as well as to compose modular networks trained independently on different task sequences into a third modular network without any fine-tuning. Finally, in search for limitations of LMC we study it on more challenging sequences of 30 and 100 tasks, demonstrating that local module selection becomes much more challenging in presence of a large number of candidate modules. In this setting best performing LMC spawns much fewer modules compared to an oracle based baseline, however, it reaches a lower overall accuracy. The codebase is available under https://github.com/oleksost/LMC.

2020-12-31

Advances in Neural Information Processing Systems 34 (NeurIPS 2021) (publié)

DATA-EFFICIENT REINFORCEMENT LEARNING

R Devon Hjelm

Philip Bachman

Aaron Courville

Data efficiency poses a major challenge for deep reinforcement learning. We approach this issue from the perspective of self-supervised repr… (voir plus)esentation learning, leveraging reward-free exploratory data to pretrain encoder networks. We employ a novel combination of latent dynamics modelling and goal-reaching objectives, which exploit the inherent structure of data in reinforcement learning. We demonstrate that our method scales well with network capacity and pretraining data. When evaluated on the Atari 100k data-efficiency benchmark, our approach significantly outperforms previous methods combining unsupervised pretraining with task-specific finetuning, and approaches human-level performance.

2020-12-31

(publié)

www.semanticscholar.org

Pretraining Representations for Data-Efficient Reinforcement Learning

Philip Bachman

Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder w… (voir plus)hich is then finetuned on a small amount of task-specific data. To encourage learning representations which capture diverse aspects of the underlying MDP, we employ a combination of latent dynamics modelling and unsupervised goal-conditioned RL. When limited to 100k steps of interaction on Atari games (equivalent to two hours of human experience), our approach significantly surpasses prior work combining offline representation pretraining with task-specific finetuning, and compares favourably with other pretraining methods that require orders of magnitude more data. Our approach shows particular promise when combined with larger models as well as more diverse, task-aligned observational data -- approaching human-level performance and data-efficiency on Atari in our best setting. We provide code associated with this work at https://github.com/mila-iqia/SGI.

2020-12-31

Advances in Neural Information Processing Systems 34 (NeurIPS 2021) (publié)

The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights

Maxime Gasse

Quentin Cappart

Jonas Charfreitag

Didier Chételat

Antonia Chmiela

Justin Dumouchelle

Ambros Gleixner

Aleksandr M. Kazachkov

Elias Khalil

Pawel Lichocki

Andrea Lodi

Miles Lubin

Chris J. Maddison

Christopher Morris

Dimitri J. Papageorgiou

Augustin Parjadis

Sebastian Pokutta

Antoine Prouvost

Lara Scavuzzo … (voir 21 de plus)

Giulia Zarpellon

Linxin Yang

Sha Lai

Akang Wang

Xiaodong Luo

Xiang Zhou

Haohan Huang

Shengcheng Shao

Yuanming Zhu

Dong Zhang

Tao Quan

Zixuan Cao

Yang Xu

Zhewei Huang

Shuchang Zhou

Chen Binbin

He Minggui

Hao Hao

Zhang Zhiyu

An Zhiwu

Mao Kun

Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused … (voir plus)on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning as a new approach for solving combinatorial problems, either directly as solvers or by enhancing exact solvers. Based on this context, the ML4CO aims at improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components. The competition featured three challenging tasks: finding the best feasible solution, producing the tightest optimality certificate, and giving an appropriate solver configuration. Three realistic datasets were considered: balanced item placement, workload apportionment, and maritime inventory routing. This last dataset was kept anonymous for the contestants.

2020-12-31

NeurIPS (Competition and Demos) (publié)

proceedings.mlr.press

Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles

Yao Lu

Yue Dong

Multi-document summarization is a challenging task for which there exists little large-scale datasets. We propose Multi-XScience, a large-sc… (voir plus)ale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challenging multi-document summarization task: writing the related-work section of a paper based on its abstract and the articles it references. Our work is inspired by extreme summarization, a dataset construction protocol that favours abstractive modeling approaches. Descriptive statistics and empirical results—using several state-of-the-art models trained on the Multi-XScience dataset—reveal that Multi-XScience is well suited for abstractive models.

2020-10-31

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (publié)

A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM

Iulian V. Serban

Varun Gupta

Ekaterina Kochmar

Dung D. Vu

Robert Belfer

2020-06-09

Artificial Intelligence in Education (publié)

Inference for travel time on transportation networks

Mohamad Elmasri

Aurélie Labbe

Denis Larocque

Travel time is essential for making travel decisions in real-world transportation networks. Understanding its distribution can resolve many … (voir plus)fundamental problems in transportation. Empirically, single-edge travel-time is well studied, but how to aggregate such information over many edges to arrive at the distribution of travel time over a route is still daunting. A range of statistical tools have been developed for network analysis; tools to study statistical behaviors of processes on dynamical networks are still lacking. This paper develops a novel statistical perspective to specific type of mixing ergodic processes (travel time), that mimic the behavior of travel time on real-world networks. Under general conditions on the single-edge speed (resistance) distribution, we show that travel time, normalized by distance, follows a Gaussian distribution with universal mean and variance parameters. We propose efficient inference methods for such parameters, and consequently asymptotic universal confidence and prediction intervals of travel time. We further develop path(route)-specific parameters that enable tighter Gaussian-based prediction intervals. We illustrate our methods with a real-world case study using mobile GPS data, where we show that the route-specific and universal intervals both achieve the 95\% theoretical coverage levels. Moreover, the route-specific prediction intervals result in tighter bounds that outperform competing models.

2020-04-22

(publié)

www.semanticscholar.org

Prediction intervals for travel time on transportation networks

Mohamad Elmasri

Aurélie Labbe

Denis Larocque

Estimating travel-time is essential for making travel decisions in transportation networks. Empirically, single road-segment travel-time is … (voir plus)well studied, but how to aggregate such information over many edges to arrive at the distribution of travel time over a route is still theoretically challenging. Understanding travel-time distribution can help resolve many fundamental problems in transportation, quantifying travel uncertainty as an example. We develop a novel statistical perspective to specific types of dynamical processes that mimic the behavior of travel time on real-world networks. We show that, under general conditions, travel-time normalized by distance, follows a Gaussian distribution with route-invariant (universal) location and scale parameters. We develop efficient inference methods for such parameters, with which we propose asymptotic universal confidence and prediction intervals of travel time. We further develop our theory to include road-segment level information to construct route-specific location and scale parameter sequences that produce tighter route-specific Gaussian-based prediction intervals. We illustrate our methods with a real-world case study using precollected mobile GPS data, where we show that the route-specific and route-invariant intervals both achieve the 95\% theoretical coverage levels, where the former result in tighter bounds that also outperform competing models.

2020-04-22

(publié)

www.semanticscholar.org

Language Gans Falling Short

Massimo Caccia

Lucas Caccia

William Fedus

Hugo Larochelle

Joelle Pineau

Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks. Maximum-Lik… (voir plus)elihood (MLE) models trained with teacher forcing have consistently been reported as weak baselines, where poor performance is attributed to exposure bias (Bengio et al., 2015; Ranzato et al., 2015); at inference time, the model is fed its own prediction instead of a ground-truth token, which can lead to accumulating errors and poor samples. This line of reasoning has led to an outbreak of adversarial based approaches for NLG, on the account that GANs do not suffer from exposure bias. In this work, we make several surprising observations which contradict common beliefs. First, we revisit the canonical evaluation framework for NLG, and point out fundamental flaws with quality-only evaluation: we show that one can outperform such metrics using a simple, well-known temperature parameter to artificially reduce the entropy of the model's conditional distributions. Second, we leverage the control over the quality / diversity trade-off given by this parameter to evaluate models over the whole quality-diversity spectrum and find MLE models constantly outperform the proposed GAN variants over the whole quality-diversity space. Our results have several implications: 1) The impact of exposure bias on sample quality is less severe than previously thought, 2) temperature tuning provides a better quality / diversity trade-off than adversarial training while being easier to train, easier to cross-validate, and less computationally expensive. Code to reproduce the experiments is available at github.com/pclucas14/GansFallingShort

2019-12-31

ICLR (publié)

Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning

Massimo Caccia

Pau Rodríguez

Lucas Caccia

Alexandre Lacoste

Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent c… (voir plus)ontinual-learning scenarios have opened new avenues of research. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation. In their original formulations, both methods have limitations. We stand on their shoulders to propose a more general scenario, OSAKA, where an agent must quickly solve new (out-of-distribution) tasks, while also requiring fast remembering. We show that current continual learning, meta-learning, meta-continual learning, and continual-meta learning techniques fail in this new scenario. We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario. We empirically show that Continual-MAML is better suited to the new scenario than the aforementioned methodologies, as well as standard continual learning and meta-learning approaches.

2019-12-31

NeurIPS (publié)