Irina Rish

Mila > About Mila > Team > Irina Rish
Core Academic Member
Irina Rish
Associate Professor, Associate Professor, Université de Montréal
Irina Rish

Irina Rish is an Associate Professor in the Computer Science and Operations Research department at the Université de Montréal (UdeM) and a core member of Mila – Quebec AI Institute. She holds the Canada CIFAR AI Chair and the Canadian Excellence Research Chair in Autonomous AI. She holds MSc and PhD in AI from University of California, Irvine and MSc in Applied Mathematics from Moscow Gubkin Institute. Dr. Rish’s research focus is on machine learning, neural data analysis and neuroscience-inspired AI.

Her current research interests include continual lifelong learning, optimization algorithms for deep neural networks, sparse modelling and probabilistic inference, dialog generation, biologically plausible reinforcement learning, and dynamical systems approaches to brain imaging analysis. Before joining UdeM and Mila in 2019, she was a research scientist at the IBM T. J. Watson Research Center, where she worked on various projects at the intersection of neuroscience and AI, and led the Neuro-AI challenge. Dr. Rish holds 64 patents, has published over 80 research papers, several book chapters, three edited books, and a monograph on Sparse Modelling.

To view Dr. Rish’s detailed CV, click here.

Publications

2021-08

Approximate Bayesian Optimisation for Neural Networks
Nadhir Hassen and Irina Rish
arXiv preprint arXiv:2108.12461
(2021-08-27)
128.84.4.18PDF
Sequoia: A Software Framework to Unify Continual Learning Research
Fabrice Normandin, Florian Golemo, Oleksiy Ostapenko, Pau Rodríguez, Matthew D. Riemer, Julio Hurtado, Khimya Khetarpal, Dominic Zhao, Ryan Lindeborg, Timothée Lesort, Laurent Charlin, Irina Rish and Massimo Caccia
arXiv preprint arXiv:2108.01005
(2021-08-02)
aps.arxiv.orgPDF

2021-07

Parametric Scattering Networks.
Shanel Gauthier, Benjamin Thérien, Laurent Alsène-Racicot, Irina Rish, Eugene Belilovsky, Michael Eickenberg and Guy Wolf
arXiv preprint arXiv:2107.09539
(2021-07-20)
ui.adsabs.harvard.eduPDF

2021-06

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Kartik Ahuja, Ethan Caballero, Dinghuai Zhang, Yoshua Bengio, Ioannis Mitliagkas and Irina Rish
arXiv: Learning
(2021-06-11)
ui.adsabs.harvard.eduPDF
Toward Skills Dialog Orchestration with Online Learning.
Djallel Bouneffouf, Raphael Feraud, Sohini Upadhyay, Mayank Agarwal, Yasaman Khazaeni and Irina Rish
ICASSP 2021
(2021-06-06)
ieeexplore.ieee.org
Double-Linear Thompson Sampling for Context-Attentive Bandits
Djallel Bouneffouf, Raphael Feraud, Sohini Upadhyay, Yasaman Khazaeni and Irina Rish
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization.
Soroosh Shahtalebi, Jean-Christophe Gagnon-Audet, Touraj Laleh, Mojtaba Faramarzi, Kartik Ahuja and Irina Rish
arXiv preprint arXiv:2106.02266
(2021-06-04)
dblp.uni-trier.dePDF
Continual Learning in Deep Networks: an Analysis of the Last Layer
Timothée Lesort, Thomas George and Irina Rish
arXiv: Learning
(2021-06-03)
ui.adsabs.harvard.eduPDF

2021-04

Gradient Masked Federated Optimization.
Irene Tenison, Sreya Francis and Irina Rish
arXiv preprint arXiv:2104.10322
(2021-04-21)
ui.adsabs.harvard.eduPDF
Towards Causal Federated Learning For Enhanced Robustness and Privacy.
Sreya Francis, Irene Tenison and Irina Rish
arXiv preprint arXiv:2104.06557
(2021-04-14)
ui.adsabs.harvard.eduPDF
Understanding Continual Learning Settings with Data Distribution Drift Analysis.
Timothée Lesort, Massimo Caccia and Irina Rish
arXiv preprint arXiv:2104.01678
(2021-04-04)
ui.adsabs.harvard.eduPDF

2021-01

Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Jenna Reinen and Irina Rish
International Workshop on Human Brain and Artificial Intelligence
(2021-01-07)
link.springer.com

2020-12

Towards Continual Reinforcement Learning: A Review and Perspectives.
Khimya Khetarpal, Matthew Riemer, Irina Rish and Doina Precup
arXiv preprint arXiv:2012.13490
(2020-12-25)
ui.adsabs.harvard.eduPDF

2020-10

Predicting Infectiousness for Proactive Contact Tracing
Yoshua Bengio, Prateek Gupta, Tegan Maharaj, Nasim Rahaman, Martin Weiss, Tristan Deleu, Eilif Muller, Meng Qu, Victor Schmidt, Pierre-Luc St-Charles, Hannah Alsdurf, Olexa Bilanuik, David Buckeridge, Gáetan Marceau Caron, Pierre-Luc Carrier, Joumana Ghosn, Satya Ortiz-Gagne, Chris Pal, Irina Rish, Bernhard Schölkopf... (3 more)
arXiv preprint arXiv:2010.12536
(2020-10-23)
ui.adsabs.harvard.eduPDF

2020-07

Survey on Applications of Multi-Armed and Contextual Bandits
Djallel Bouneffouf, Irina Rish and Charu Aggarwal
CEC 2020
(2020-07-19)
doi.org

2020-05

COVI White Paper.
Hannah Alsdurf, Yoshua Bengio, Tristan Deleu, Prateek Gupta, Daphne Ippolito, Richard Janda, Max Jarvie, Tyler Kolody, Sekoul Krastev, Tegan Maharaj, Robert Obryk, Dan Pilat, Valerie Pisano, Benjamin Prud'homme, Meng Qu, Nasim Rahaman, Irina Rish, Jean-Franois Rousseau, Abhinav Sharma, Brooke Struck... (3 more)
arXiv preprint arXiv:2005.08502
(2020-05-18)
europepmc.orgPDF
An Empirical Study of Human Behavioral Agents in Bandits, Contextual Bandits and Reinforcement Learning
Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Jenna Reinen and Irina Rish
arXiv: Artificial Intelligence
(2020-05-10)
ui.adsabs.harvard.eduPDF
Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
Baihan Lin, Guillermo A. Cecchi, Djallel Bouneffouf, Jenna Reinen and Irina Rish
(venue unknown)
(2020-05-10)
dblp.uni-trier.de
A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry
Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Jenna Reinen and Irina Rish
AAMAS 2020
(2020-05-05)
dl.acm.org

2020-04

Modeling Dialogues with Hashcode Representations: A Nonparametric Approach
Sahil Garg, Irina Rish, Guillermo A. Cecchi, Palash Goyal, Sarik Ghazarian, Shuyang Gao, Greg Ver Steeg and Aram Galstyan
AAAI 2020
(2020-04-03)
aaai.org

2020-03

Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
Victor Schmidt, Makesh Narsimhan Sreedhar, Mostafa ElAraby and Irina Rish
arXiv: Computer Vision and Pattern Recognition
(2020-03-31)
ui.adsabs.harvard.eduPDF
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Caccia, Issam Laradji, Irina Rish, Alexandre Lacoste, David Vazquez and Laurent Charlin
arXiv preprint arXiv:2003.05856
(2020-03-12)
arxiv.orgPDF

2020-01

Resting-state connectivity stratifies premanifest Huntington's disease by longitudinal cognitive decline rate.
Pablo Polosecki, Eduardo Castro, Irina Rish, Dorian Pustina, John H. Warner, Andrew Wood, Cristina Sampaio and Guillermo A. Cecchi
Scientific Reports
(2020-01-27)
www.nature.com
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Page-Caccia, Issam Hadj Laradji, Irina Rish, Alexandre Lacoste, David Vázquez and Laurent Charlin
NEURIPS 2020
(2020-01-01)
papers.nips.ccPDF

Publications collected and formatted using Paperoni

array(1) { ["wp-wpml_current_language"]=> string(2) "en" }