Irina Rish

Biography

Irina Rish is a full professor at the Université de Montréal (UdeM), where she leads the Autonomous AI Lab, and a core academic member of Mila – Quebec Artificial Intelligence Institute.

In addition to holding a Canada Excellence Research Chair (CERC) and a CIFAR Chair, she leads the U.S. Department of Energy’s INCITE project on Scalable Foundation Models on Summit & Frontier supercomputers at the Oak Ridge Leadership Computing Facility. She co-founded and serves as CSO of Nolano.ai.

Rish’s current research interests include neural scaling laws and emergent behaviors (capabilities and alignment) in foundation models, as well as continual learning, out-of-distribution generalization and robustness.

Before joining UdeM 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. She was awarded the IBM Eminence & Excellence Award and IBM Outstanding Innovation Award (2018), IBM Outstanding Technical Achievement Award (2017) and IBM Research Accomplishment Award (2009).

She holds 64 patents and has published 120 research papers, several book chapters, three edited books and a monograph on sparse modeling.

Current Students

Germán Abrevaya

Independent visiting researcher - Université de Montréal

Co-supervisor :

Research Intern

PhD - Université de Montréal

Co-supervisor :

Samira Ebrahimi Kahou

Rifat Arefin

PhD - Université de Montréal

Arjun Ashok

PhD - Université de Montréal

Co-supervisor :

Reza Bayat

Master's Research - Université de Montréal

Co-supervisor :

Pouya Bashivan

Rishika Bhagwatkar

Master's Research - Université de Montréal

Collaborating researcher - Université de Montréal

Ethan Caballero

PhD - McGill University

Principal supervisor :

Blake Richards

Mohammad-javad Darvishi-bayazi Darvishi Bayazi

Amin Darabi

PhD - Université de Montréal

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Karim Jerbi

Mojtaba Faramarzi

PhD - Université de Montréal

Kshitij Gupta

Collaborating Alumni - Université de Montréal

Co-supervisor :

Sarath Chandar

Nadhir Hassen

Research Intern - Université de Montréal

Master's Research

PhD - Université de Montréal

Principal supervisor :

Ioannis Mitliagkas

Nizar Islah

PhD - Université de Montréal

Principal supervisor :

Eilif Benjamin Muller

PhD - Université de Montréal

Collaborating researcher

Zafir Khalid

Master's Research - Concordia University

Principal supervisor :

Master's Research - Université de Montréal

Neeraj Kumar

Professional Master's - Université de Montréal

Gwen Legate

PhD - Concordia University

Principal supervisor :

Eugene Belilovsky

David Lemay

Master's Research - Université de Montréal

amin.mansouri@mila.quebec

Ekaterina Lobacheva

Postdoctorate - Université de Montréal

Principal supervisor :

Master's Research - Université de Montréal

Collaborating Alumni

PhD - Université de Montréal

Master's Research - Université de Montréal

Diganta Misra

Master's Research - Université de Montréal

Remus Mocanu

Master's Research - Université de Montréal

Timothy Nest

PhD - Université de Montréal

Co-supervisor :

Eilif Benjamin Muller

Mohammad Pezeshki

Collaborating researcher

Motahareh Pourrahimi

PhD - McGill University

Principal supervisor :

Pouya Bashivan

Mahta Ramezanian

Master's Research - Université de Montréal

Co-supervisor :

Guillaume Dumas

Roland Riachi

Collaborating researcher - Université de Montréal

Matthew Riemer

PhD - Université de Montréal

Alexis Roger

PhD - McGill University

Principal supervisor :

Blake Richards

Zahra Sheikhbahaee

Postdoctorate - Université de Montréal

Principal supervisor :

Guillaume Dumas

Vaibhav Singh

PhD - Concordia University

Principal supervisor :

Eugene Belilovsky

Gopeshh Subbaraj

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Master's Research - Université de Montréal

Dave Whipps

Master's Research - Université de Montréal

Andrew Williams

PhD - Université de Montréal

Daria Yasafova

Master's Research - Université de Montréal

Omar Younis

Collaborating researcher

Principal supervisor :

Yoshua Bengio

Publications

Cognitive Models as Simulators: The Case of Moral Decision-Making

Ardavan S. Nobandegani

T. Shultz

2022-01-01

CogSci (published)

Compositional Attention: Disentangling Search and Retrieval

Sarthak Mittal

Sharath Chandra Raparthy

Yoshua Bengio

Guillaume Lajoie

Multi-head, key-value attention is the backbone of transformer-like model architectures which have proven to be widely successful in recent … (see more)years. This attention mechanism uses multiple parallel key-value attention blocks (called heads), each performing two fundamental computations: (1) search - selection of a relevant entity from a set via query-key interaction, and (2) retrieval - extraction of relevant features from the selected entity via a value matrix. Standard attention heads learn a rigid mapping between search and retrieval. In this work, we first highlight how this static nature of the pairing can potentially: (a) lead to learning of redundant parameters in certain tasks, and (b) hinder generalization. To alleviate this problem, we propose a novel attention mechanism, called Compositional Attention, that replaces the standard head structure. The proposed mechanism disentangles search and retrieval and composes them in a dynamic, flexible and context-dependent manner. Through a series of numerical experiments, we show that it outperforms standard multi-head attention on a variety of tasks, including some out-of-distribution settings. Through our qualitative analysis, we demonstrate that Compositional Attention leads to dynamic specialization based on the type of retrieval needed. Our proposed mechanism generalizes multi-head attention, allows independent scaling of search and retrieval and is easy to implement in a variety of established network architectures.

2022-01-01

International Conference on Learning Representations (published)

Continual Learning In Environments With Polynomial Mixing Times

Matthew D Riemer

Sharath Chandra Raparthy

Ignacio Cases

Gopeshh Raaj Subbaraj

Maximilian Puelma Touzel

The mixing time of the Markov chain induced by a policy limits performance in real-world continual learning scenarios. Yet, the effect of mi… (see more)xing times on learning in continual reinforcement learning (RL) remains underexplored. In this paper, we characterize problems that are of long-term interest to the development of continual RL, which we call scalable MDPs, through the lens of mixing times. In particular, we theoretically establish that scalable MDPs have mixing times that scale polynomially with the size of the problem. We go on to demonstrate that polynomial mixing times present significant difficulties for existing approaches that suffer from myopic bias and stale bootstrapped estimates. To validate the proposed theory, we study the empirical scaling behavior of mixing times with respect to the number of tasks and task switching frequency for pretrained high performing policies on seven Atari games. Our analysis demonstrates both that polynomial mixing times do emerge in practice and how their existence may lead to unstable learning behavior like catastrophic forgetting in continual learning settings.

Continual Learning with Foundation Models: An Empirical Study of Latent Replay

Oleksiy Ostapenko

Timothee LESORT

Pau Rodriguez

Md Rifat Arefin

Arthur Douillard

Laurent Charlin

2022-01-01

CoLLAs (published)

Optimizing deep learning for Magnetoencephalography (MEG): From sensory perception to sex prediction and brain fingerprinting

Arthur Dehgan

Karim Jerbi

2022-01-01

2022 Conference on Cognitive Computational Neuroscience (published)

Scaling the Number of Tasks in Continual Learning

Timothee LESORT

Oleksiy Ostapenko

Diganta Misra

Md Rifat Arefin

Pau Rodriguez

Laurent Charlin

2022-01-01

arXiv.org (preprint)

Generative Models of Brain Dynamics -- A review

Mahta Ramezanian Panahi

Germán Abrevaya

Jean-Christophe Gagnon-Audet

Vikram Voleti

Guillaume Dumas

The principled design and discovery of biologically- and physically-informed models of neuronal dynamics has been advancing since the mid-tw… (see more)entieth century. Recent developments in artificial intelligence (AI) have accelerated this progress. This review article gives a high-level overview of the approaches across different scales of organization and levels of abstraction. The studies covered in this paper include fundamental models in computational neuroscience, nonlinear dynamics, data-driven methods, as well as emergent practices. While not all of these models span the intersection of neuroscience, AI, and system dynamics, all of them do or can work in tandem as generative models, which, as we argue, provide superior properties for the analysis of neuroscientific data. We discuss the limitations and unique dynamical traits of brain data and the complementary need for hypothesis- and data-driven modeling. By way of conclusion, we present several hybrid generative models from recent literature in scientific machine learning, which can be efficiently deployed to yield interpretable models of neural dynamics.

2021-12-22

ArXiv (preprint)

Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers

Gabriele Prato

Simon Guiroy

Ethan Caballero

Sarath Chandar

Empirical science of neural scaling laws is a rapidly growing area of significant importance to the future of machine learning, particularly… (see more) in the light of recent breakthroughs achieved by large-scale pre-trained models such as GPT-3, CLIP and DALL-e. Accurately predicting the neural network performance with increasing resources such as data, compute and model size provides a more comprehensive evaluation of different approaches across multiple scales, as opposed to traditional point-wise comparisons of fixed-size models on fixed-size benchmarks, and, most importantly, allows for focus on the best-scaling, and thus most promising in the future, approaches. In this work, we consider a challenging problem of few-shot learning in image classification, especially when the target data distribution in the few-shot phase is different from the source, training, data distribution, in a sense that it includes new image classes not encountered during training. Our current main goal is to investigate how the amount of pre-training data affects the few-shot generalization performance of standard image classifiers. Our key observations are that (1) such performance improvements are well-approximated by power laws (linear log-log plots) as the training set size increases, (2) this applies to both cases of target data coming from either the same or from a different domain (i.e., new classes) as the training data, and (3) few-shot performance on new classes converges at a faster rate than the standard classification performance on previously seen classes. Our findings shed new light on the relationship between scale and generalization.

2021-10-13

ArXiv (preprint)

Approximate Bayesian Optimisation for Neural Networks

Nadhir Hassen

2021-08-27

ArXiv (preprint)

Toward Optimal Solution for the Context-Attentive Bandit Problem

Djallel Bouneffouf

Raphael Feraud

Sohini Upadhyay

Yasaman Khazaeni

2021-08-19

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (published)

Sequoia: A Software Framework to Unify Continual Learning Research

Fabrice Normandin

Oleksiy Ostapenko

Pau Rodriguez

Florian Golemo

Ryan Lindeborg

J. Hurtado

Matthew D Riemer

Lucas Cecchi

Timothee LESORT

Dominic Zhao

Khimya Khetarpal

David Vazquez

Laurent Charlin

Massimo Caccia

The field of Continual Learning (CL) seeks to develop algorithms that accumulate knowledge and skills over time through interaction with non… (see more)-stationary environments. In practice, a plethora of evaluation procedures (settings) and algorithmic solutions (methods) exist, each with their own potentially disjoint set of assumptions. This variety makes measuring progress in CL difficult. We propose a taxonomy of settings, where each setting is described as a set of assumptions. A tree-shaped hierarchy emerges from this view, where more general settings become the parents of those with more restrictive assumptions. This makes it possible to use inheritance to share and reuse research, as developing a method for a given setting also makes it directly applicable onto any of its children. We instantiate this idea as a publicly available software framework called Sequoia, which features a wide variety of settings from both the Continual Supervised Learning (CSL) and Continual Reinforcement Learning (CRL) domains. Sequoia also includes a growing suite of methods which are easy to extend and customize, in addition to more specialized methods from external libraries. We hope that this new paradigm and its first implementation can help unify and accelerate research in CL. You can help us grow the tree by visiting (this GitHub URL).

2021-08-02

ArXiv (preprint)

Parametric Scattering Networks

Shanel Gauthier

Benjamin Th'erien

Laurent Alséne-Racicot

Eugene Belilovsky

Michael Eickenberg

Guy Wolf

The wavelet scattering transform creates geometric in-variants and deformation stability. In multiple signal do-mains, it has been shown to … (see more)yield more discriminative rep-resentations compared to other non-learned representations and to outperform learned representations in certain tasks, particularly on limited labeled data and highly structured signals. The wavelet filters used in the scattering trans-form are typically selected to create a tight frame via a pa-rameterized mother wavelet. In this work, we investigate whether this standard wavelet filterbank construction is op-timal. Focusing on Morlet wavelets, we propose to learn the scales, orientations, and aspect ratios of the filters to produce problem-specific parameterizations of the scattering transform. We show that our learned versions of the scattering transform yield significant performance gains in small-sample classification settings over the standard scat-tering transform. Moreover, our empirical results suggest that traditional filterbank constructions may not always be necessary for scattering transforms to extract effective rep-resentations.

2021-07-20

ArXiv (preprint)