Laurent Charlin

Biography

Laurent Charlin is a Canada CIFAR AI Chair at Mila and an associate professor at HEC, the business school affiliated with the University de Montréal. He is also a core member of Mila—Quebec Institute for Artificial Intelligence.

Charlin’s research focuses on developing novel machine learning models to aid in decision-making. Recent work has focused on learning from data that changes over time, and on applications in fields such as recommender systems and optimization.

He has a number of highly cited publications on dialogue systems (chatbots). He co-developed the Toronto Paper Matching System (TPMS), which has been widely used by computer science conferences for matching reviewers to papers. He has also given MOOCs, introductory talks and media interviews to contribute to knowledge transfer and improve AI literacy.

Current Students

Neda Adl

Master's Research - HEC Montréal

Neda@mila.quebec

Anirudh Buvanesh

PhD - Université de Montréal

Co-supervisor :

Aaron Courville

anirudb1102@gmail.com

felix.gauthier@mila.quebec

Félix Gauthier

Master's Research - HEC Montréal

Soraya Ghassemlou

Master's Research - McGill University

soraya.ghassemlou@mila.quebec

Website

nicolas.goulet@mila.quebec

Nicolas Goulet

PhD - HEC Montréal

Principal supervisor :

Eva Portelance

shubham.gupta@mila.quebec

Shubham Gupta

PhD - Université Laval

Principal supervisor :

Cem Subakan

Ben Hudson

PhD - Université de Montréal

Co-supervisor :

Emma Frejinger

ben.hudson@mila.quebec

Website

mizu.nishikawa-toomey@mila.quebec

Mizu Nishikawa-Toomey

PhD - Université de Montréal

Co-supervisor :

Dhanya Sridhar

PhD - Concordia University

Principal supervisor :

Mirco Ravanelli

firat.oncel@mila.quebec

Collaborating Alumni - Université de Montréal

ostapeno@mila.quebec

emiliano.penaloza@mila.quebec

Emiliano Penaloza

PhD - Université de Montréal

Website

omar.salemohamed@mila.quebec

Gaurav Sahu

Postdoctorate - HEC Montréal

Co-supervisor :

Chris Pal

gaurav.sahu@mila.quebec

PhD - Université de Montréal

Yipeng Zhang

PhD - Université de Montréal

yipeng.zhang@mila.quebec

Publications

Operational Research: Methods and Applications

Fotios Petropoulos

Gilbert Laporte

Emel Aktas

Sibel A. Alumur

Claudia Archetti

Hayriye Ayhan

Maria Battarra

Julia A. Bennell

Jean-Marie Bourjolly

John E. Boylan

Michele Breton

David Canca

Bo Chen

Cihan Tugrul Cicek

Louis Anthony Cox, Jr

Christine S.M. Currie

Erik Demeulemeester

Li Ding

Stephen M. Disney … (see 62 more)

Matthias Ehrgott

Martin J. Eppler

Gunes Erdogan

Bernard Fortz

L. Alberto Franco

Jens Frische

Salvatore Greco

Amanda J. Gregory

Raimo P. Hamalainen

Willy Herroelen

Mike Hewitt

Jan Holmstrom

John N. Hooker

Tugce Isik

Jill Johnes

Bahar Y. Kara

Ozlem Karsu

Katherine Kent

Charlotte Kohler

Martin Kunc

Yong-Hong Kuo

Judit Lienert

Adam N. Letchford

Janny Leung

Dong Li

Haitao Li

Ivana Ljubic

Andrea Lodi

Sebastian Lozano

Virginie Lurkin

Silvano Martello

Ian G. McHale

Gerald Midgley

John D.W. Morecroft

Akshay Mutha

Ceyda Oguz

Sanja Petrovic

Ulrich Pferschy

Harilaos N. Psaraftis

Sam Rose

Lauri Saarinen

Said Salhi

Jing-Sheng Song

Dimitrios Sotiros

Kathryn E. Stecke

Arne K. Strauss

Istenc Tarhan

Clemens Thielen

Paolo Toth

Greet Vanden Berghe

Christos Vasilakis

Vikrant Vaze

Daniele Vigo

Kai Virtanen

Xun Wang

Rafał Weron

Leroy White

Tom Van Woensel

Mike Yearworth

E. Alper Yıldırım

Georges Zaccour

Xuying Zhao

Throughout its history, Operational Research has evolved to include a variety of methods, models and algorithms that have been applied to a … (see more)diverse and wide range of contexts. This encyclopedic article consists of two main sections: methods and applications. The first aims to summarise the up-to-date knowledge and provide an overview of the state-of-the-art methods and key developments in the various subdomains of the field. The second offers a wide-ranging list of areas where Operational Research has been applied. The article is meant to be read in a nonlinear fashion. It should be used as a point of reference or first-port-of-call for a diverse pool of readers: academics, researchers, students, and practitioners. The entries within the methods and applications sections are presented in alphabetical order. The authors dedicate this paper to the 2023 Turkey/Syria earthquake victims. We sincerely hope that advances in OR will play a role towards minimising the pain and suffering caused by this and future catastrophes.

2023-12-31

J. Oper. Res. Soc. (published)

arxiv.org

Towards Modular LLMs by Building and Reusing a Library of LoRAs

Matheus Pereira

Lucas Caccia

Alessandro Sordoni

The growing number of parameter-efficient adaptations of a base large language model (LLM) calls for studying whether we can reuse such trai… (see more)ned adapters to improve performance for new tasks. We study how to best build a library of adapters given multi-task data and devise techniques for both zero-shot and supervised task generalization through routing in such library. We benchmark existing approaches to build this library and introduce model-based clustering, MBC, a method that groups tasks based on the similarity of their adapter parameters, indirectly optimizing for transfer across the multi-task dataset. To re-use the library, we present a novel zero-shot routing mechanism, Arrow, which enables dynamic selection of the most relevant adapters for new inputs without the need for retraining. We experiment with several LLMs, such as Phi-2 and Mistral, on a wide array of held-out tasks, verifying that MBC-based adapters and Arrow routing lead to superior generalization to new tasks. We make steps towards creating modular, adaptable LLMs that can match or outperform traditional joint training.

2023-12-31

ICML (published)

Predictive inference for travel time on transportation networks

Mohamad Elmasri

Aurélie Labbe

Denis Larocque

2023-11-30

The Annals of Applied Statistics (published)

arxiv.org

Challenging Common Assumptions About Catastrophic Forgetting and Knowledge Accumulation

Timothee LESORT

Pau Rodríguez

Md Rifat Arefin

Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research fiel… (see more)d. Unfortunately, training a model on new data usually compromises the performance on past data. In the CL literature, this effect is referred to as catastrophic forgetting (CF). CF has been largely studied, and a plethora of methods have been proposed to address it on short sequences of non-overlapping tasks. In such setups, CF always leads to a quick and significant drop in performance in past tasks. Nevertheless, despite CF, recent work showed that SGD training on linear models accumulates knowledge in a CL regression setup. This phenomenon becomes especially visible when tasks reoccur. We might then wonder if DNNs trained with SGD or any standard gradient-based optimization accumulate knowledge in such a way. Such phenomena would have interesting consequences for applying DNNs to real continual scenarios. Indeed, standard gradient-based optimization methods are significantly less computationally expensive than existing CL algorithms. In this paper, we study the progressive knowledge accumulation (KA) in DNNs trained with gradient-based algorithms in long sequences of tasks with data re-occurrence. We propose a new framework, SCoLe (Scaling Continual Learning), to investigate KA and discover that catastrophic forgetting has a limited effect on DNNs trained with SGD. When trained on long sequences with data sparsely re-occurring, the overall accuracy improves, which might be counter-intuitive given the CF phenomenon. We empirically investigate KA in DNNs under various data occurrence frequencies and propose simple and scalable strategies to increase knowledge accumulation in DNNs.

2023-11-19

Conference on Lifelong Learning Agents (published)

Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges

Massimo Caccia

Jonas Mueller

Taesup Kim

Rasool Fakoor

2023-11-19

Proceedings of The 2nd Conference on Lifelong Learning Agents (published)

A Case Study of Instruction Tuning with Mixture of Parameter-Efficient Experts

O. Ostapenko

Lucas Caccia

2023-10-27

NeurIPS.cc/2023/Workshop/Instruction (published)

openreview.net

Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network

Tristan Deleu

Mizu Nishikawa-Toomey

Jithendaraa Subramanian

Nikolay Malkin

Yoshua Bengio

Generative Flow Networks (GFlowNets), a class of generative models over discrete and structured sample spaces, have been previously applied … (see more)to the problem of inferring the marginal posterior distribution over the directed acyclic graph (DAG) of a Bayesian Network, given a dataset of observations. Based on recent advances extending this framework to non-discrete sample spaces, we propose in this paper to approximate the joint posterior over not only the structure of a Bayesian Network, but also the parameters of its conditional probability distributions. We use a single GFlowNet whose sampling policy follows a two-phase process: the DAG is first generated sequentially one edge at a time, and then the corresponding parameters are picked once the full structure is known. Since the parameters are included in the posterior distribution, this leaves more flexibility for the local probability models of the Bayesian Network, making our approach applicable even to non-linear models parametrized by neural networks. We show that our method, called JSP-GFN, offers an accurate approximation of the joint posterior, while comparing favorably against existing methods on both simulated and real data.

2023-09-20

NeurIPS.cc/2023/Conference (poster)

openreview.net

Should We Feed the Trolls? Using Marketer-Generated Content to Explain Average Toxicity and Product Usage

Marcelo Vinhal Nepomuceno

Hooman Rahemi

Tolga Cenesizoglu

2023-06-28

Journal of Interactive Marketing (published)

Towards Compute-Optimal Transfer Learning

Massimo Caccia

Alexandre Galashov

Arthur Douillard

Amal Rannen-Triki

Dushyant Rao

Michela Paganini

Marc'aurelio Ranzato

Razvan Pascanu

2023-04-24

ArXiv (preprint)

arxiv.org

From IID to the Independent Mechanisms assumption in continual learning

Oleksiy Ostapenko

Pau Rodríguez

Alexandre Lacoste

2023-01-10

AAAI.org/2023/Bridge/CCBridge (accepted)

Iorl: Inductive-Offline-Reinforcement-Learning for Traffic Signal Control Warmstarting

FranÃ§ois-Xavier Devailly

Denis Larocque

2022-12-31

Social Science Research Network (published)

Price forecasting in the Ontario electricity market via TriConvGRU hybrid model: Univariate vs. multivariate frameworks

Behdad Ehsani

Pierre-Olivier Pineau

Electricity price forecasting is a challenging task for decision-makers in deregulated power markets due to the inherent characteristics of … (see more)electricity prices, e.g., high frequency and volatility. Therefore, accurate forecasting of electricity prices can assist market participants in maximizing their profit. Accordingly, we proposed a novel hybrid Deep Learning model to forecast one-step, two-step, and three-step ahead Ontario electricity prices based on a Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU). Our model consists of three consecutive CNN-GRU models combined in parallel with different input data. We downsampled input data via pooling layers at the beginning of two streams of the model to capture different frequencies of price patterns concurrently. Also, a set of external variables, including previous prices, electricity load, generation, import and export, and weather data, were considered in our forecasting models to test whether these features improve the efficiency of the models. Finally, three experiments in various weeks of 2022 were carried out in the Ontario electricity market to assess the model. The results indicate that the proposed model reduced the forecasting error significantly by 63.3% in the first experiment, 41.8% in the second, and 28.2% in the third, on average, with respect to a Root Mean Square Error (RMSE). Also, the proposed model was compared with outperformed several baseline models, including statistical time-series, Machine Learning, and Deep Learning models. Furthermore, the comparison of results in univariate and multivariate settings indicated that adding variables to forecasting models did not help reduce forecasting errors.

2022-12-31

SSRN Electronic Journal (unknown)