Portrait of Sarath Chandar

Sarath Chandar

Core Academic Member

sarath.chandar@mila.quebec

Canada CIFAR AI Chair

Associate Professor, Polytechnique Montréal, Department of Computer Engineering and Software Engineering

Adjunct Professor, Université de Montréal, Department of Computer Science and Operations Research

Indian Institute of Technology Madras

Research Topics

AI Alignment

Deep Learning

Explainable AI (XAI)

Foundation Models

Interpretability

Large Language Models (LLM)

Lifelong Learning

Medical Machine Learning

Multi-Agent Systems

Natural Language Processing

Online Learning

Optimization

Recurrent Neural Networks

Reinforcement Learning

Representation Learning

Transfer Learning

Trustworthy AI

Biography

Sarath Chandar is an associate professor at Polytechnique Montreal's Department of Computer and Software Engineering, where he leads the Chandar Research Lab. He is also a Core Academic Member at Mila – Quebec Artificial Intelligence Institute and holds a Canada CIFAR AI Chair and the Canada Research Chair in Lifelong Machine Learning.

Chandar’s research interests include lifelong learning, deep learning, optimization, reinforcement learning and natural language processing. To promote research in lifelong learning, Chandar created the Conference on Lifelong Learning Agents (CoLLAs) in 2022, for which he served as program chair in 2022 and 2023.

He has a PhD from Université de Montréal and an MSc (By Research) from the Indian Institute of Technology Madras.

Current Students

Master's Research - Université de Montréal

Davide Baldelli

PhD - Polytechnique Montréal

Co-supervisor :

Antoine Clavaud

Master's Research - Polytechnique Montréal

PhD - Polytechnique Montréal

Principal supervisor :

Naga Karthik Enamundram

PhD - Polytechnique Montréal

Principal supervisor :

Julien Cohen-Adad

emvnagakarthik@gmail.com

Prashant Govindarajan

PhD - Polytechnique Montréal

PhD - Université de Montréal

Principal supervisor :

Collaborating researcher - Université de Montréal

Principal supervisor :

Maryam Hashemzadeh

PhD - Université de Montréal

David Heurtel--Depeiges

PhD - Polytechnique Montréal

PhD - Université de Montréal

Amir Ardalan Kalantari Dehaghi

Collaborating Alumni

Master's Research - Polytechnique Montréal

PhD - Polytechnique Montréal

Co-supervisor :

andreas.madsen@mila.quebec

Pranshu Malviya

PhD - Polytechnique Montréal

Master's Research - Polytechnique Montréal

Mohamed Amine Merzouk

Postdoctorate - Polytechnique Montréal

Principal supervisor :

Hadi NekoeiQachkanloo

PhD - Université de Montréal

PhD - Université de Montréal

PhD - Université de Montréal

Janarthanan Rajendran

Collaborating Alumni - Université de Montréal

Co-supervisor :

Mathieu Reymond

Postdoctorate

Francois Rivest

Independent visiting researcher

Mohammad R. Samsami

Master's Research - Université de Montréal

Master's Research - Université de Montréal

Arjun Vaithilingam Sudhakar

PhD - Polytechnique Montréal

Abdelrahman Zayed

PhD - Polytechnique Montréal

PhD - Polytechnique Montréal

PhD - Polytechnique Montréal

Blog Posts

A digital picture of Bert from Sesame street, wering black trench coat and sunglasses

March 3, 2025

NeoBERT: A New Frontier for Open-Source Encoder Language Models

by

Quentin Fournier

Read the article

October 1, 2024

How Do We Explain AI and Ensure the Explanation Is True? Faithfulness Measurable Models Tell You How

by

Siva Reddy

Read the article

Publications

Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study

Chinnadhurai Sankar

Sandeep Subramanian

Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily ad… (see more)apted to new domains, and require minimal domain engineering. A common criticism of these systems is that they seldom understand or use the available dialog history effectively. In this paper, we take an empirical approach to understanding how these models use the available dialog history by studying the sensitivity of the models to artificially introduced unnatural changes or perturbations to their context at test time. We experiment with 10 different types of perturbations on 4 multi-turn dialog datasets and find that commonly used neural dialog architectures like recurrent and transformer-based seq2seq models are rarely sensitive to most perturbations such as missing or reordering utterances, shuffling words, etc. Also, by open-sourcing our code, we believe that it will serve as a useful diagnostic tool for evaluating dialog systems in the future.

2019-07-01

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (published)

Environments for Lifelong Reinforcement Learning

Khimya Khetarpal

Shagun Sodhani

To achieve general artificial intelligence, reinforcement learning (RL) agents should learn not only to optimize returns for one specific ta… (see more)sk but also to constantly build more complex skills and scaffold their knowledge about the world, without forgetting what has already been learned. In this paper, we discuss the desired characteristics of environments that can support the training and evaluation of lifelong reinforcement learning agents, review existing environments from this perspective, and propose recommendations for devising suitable environments in the future.

2018-11-26

ArXiv (preprint)

On Training Recurrent Neural Networks for Lifelong Learning

Shagun Sodhani

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we stud… (see more)y these challenges in the context of sequential supervised learning with emphasis on recurrent neural networks. To evaluate the models in the lifelong learning setting, we propose a curriculum-based, simple, and intuitive benchmark where the models are trained on tasks with increasing levels of difficulty. To measure the impact of catastrophic forgetting, the model is tested on all the previous tasks as it completes any task. As a step towards developing true lifelong learning systems, we unify Gradient Episodic Memory (a catastrophic forgetting alleviation approach) and Net2Net(a capacity expansion approach). Both these models are proposed in the context of feedforward networks and we evaluate the feasibility of using them for recurrent networks. Evaluation on the proposed benchmark shows that the unified model is more suitable than the constituent models for lifelong learning setting.

2018-11-16

ArXiv (preprint)