Sarath Chandar

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

Istabrak Abbes

Master's Research - Université de Montréal

Alex Aselstyne

Master's Research - Polytechnique Montréal

Davide Baldelli

PhD - Polytechnique Montréal

Co-supervisor :

Milan Bhan

Collaborating researcher

Diego Cerda Mardini

Master's Research - McGill University

Antoine Clavaud

Master's Research - Polytechnique Montréal

Naga Karthik Enamundram

PhD - Polytechnique Montréal

Principal supervisor :

Prashant Govindarajan

PhD - Polytechnique Montréal

Simon Guiroy

PhD - Université de Montréal

Principal supervisor :

Collaborating researcher

Principal supervisor :

Irina Rish

Maryam Hashemzadeh

PhD - Université de Montréal

David Heurtel--Depeiges

PhD - Polytechnique Montréal

Jerry Huang

PhD - Université de Montréal

Saurav Jha

Postdoctorate - Polytechnique Montréal

Amir Kalantari Dehaghi

Collaborating Alumni

Lola Le Breton

PhD - Polytechnique Montréal

Aidan Li

Master's Research - Université de Montréal

Co-supervisor :

Postdoctorate - Université de Montréal

PhD - Polytechnique Montréal

Roshan Munirathinam Sankaran Balaji

Collaborating researcher - Polytechnique Montréal

Hadi NekoeiQachkanloo

PhD - Université de Montréal

Nilaksh Nilaksh

PhD - Polytechnique Montréal

PhD - Université de Montréal

Linda Peinthiere

Collaborating researcher - Polytechnique Montréal Montreal

Yann Pernot

Master's Research - Polytechnique Montréal

Gabriele Prato

PhD - Université de Montréal

Collaborating Alumni

Shaipranesh Senthilkumar

PhD - Polytechnique Montréal

Arjun Vaithilingam Sudhakar

Nour Shaheen

Master's Research - Polytechnique Montréal

Principal supervisor :

PhD - Polytechnique Montréal

Anabel Tan

Postdoctorate - Université de Montréal

Megh Thakkar

Master's Research - Université de Montréal

PhD - Polytechnique Montréal

Shawn Whitfield

Collaborating researcher

Abdelrahman Zayed

PhD - Polytechnique Montréal

Xutong Zhao

PhD - Polytechnique Montréal

Artem Zholus

PhD - Polytechnique Montréal

Improving CAD Design With LLMs

Blog Posts

December 19, 2025

Prashant Govindarajan

Davide Baldelli

Quentin Fournier

Sarath Chandar

Read the article

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

Lola Le Breton

Quentin Fournier

Sarath Chandar

Read the article

October 1, 2024

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

Andrea Madsen

Siva Reddy

Sarath Chandar

Read the article

Publications

Towards Non-Saturating Recurrent Units for Modelling Long-Term Dependencies

Sarath Chandar

Chinnadhurai Sankar

Eugene Vorontsov

Samira Ebrahimi Kahou

Yoshua Bengio

Modelling long-term dependencies is a challenge for recurrent neural networks. This is primarily due to the fact that gradients vanish durin… (see more)g training, as the sequence length increases. Gradients can be attenuated by transition operators and are attenuated or dropped by activation functions. Canonical architectures like LSTM alleviate this issue by skipping information through a memory mechanism. We propose a new recurrent architecture (Non-saturating Recurrent Unit; NRU) that relies on a memory mechanism but forgoes both saturating activation functions and saturating gates, in order to further alleviate vanishing gradients. In a series of synthetic and real world tasks, we demonstrate that the proposed model is the only model that performs among the top 2 models across all tasks with and without long-term dependencies, when compared against a range of other architectures.

2019-07-16

Proceedings of the AAAI Conference on Artificial Intelligence (published)

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

Christopher Pal

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.

2019-06-30

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

Environments for Lifelong Reinforcement Learning

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.

2018-11-25

ArXiv (preprint)

Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes

We extend the neural Turing machine (NTM) model into a dynamic neural Turing machine (D-NTM) by introducing trainable address vectors. This … (see more)addressing scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing strategies, including both linear and nonlinear ones. We implement the D-NTM with both continuous and discrete read and write mechanisms. We investigate the mechanisms and effects of learning to read and write into a memory through experiments on Facebook bAbI tasks using both a feedforward and GRU controller. We provide extensive analysis of our model and compare different variations of neural Turing machines on this task. We show that our model outperforms long short-term memory and NTM variants. We provide further experimental results on the sequential [Formula: see text]MNIST, Stanford Natural Language Inference, associative recall, and copy tasks.

2018-03-31

Neural Computation (published)

openreview.net

A Deep Reinforcement Learning Chatbot (Short Version)

Iulian V. Serban

Mathieu Germain

Michael Pieper

Nan Rosemary Ke

Sai Rajeswar

Alexandre De Brébisson

Jose M. R. Sotelo

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon … (see more)Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including neural network and template-based models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than other systems. The results highlight the potential of coupling ensemble systems with deep reinforcement learning as a fruitful path for developing real-world, open-domain conversational agents.

2017-12-31

arXiv (preprint)

A Deep Reinforcement Learning Chatbot

Iulian V. Serban

Mathieu Germain

Michael Pieper

Nan Rosemary Ke

Sai Mudumba

Alexandre De Brébisson

Jose M. R. Sotelo

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon … (see more)Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than many competing systems. Due to its machine learning architecture, the system is likely to improve with additional data.

2017-09-06

ArXiv (preprint)