Irina Rish

Biographie

Irina Rish est professeure titulaire à l'Université de Montréal (UdeM), où elle dirige le Laboratoire d'IA autonome. Membre du corps professoral de Mila – Institut québécois d’intelligence artificielle, elle est titulaire d'une chaire d'excellence en recherche du Canada (CERC) et d'une chaire en IA Canada-CIFAR. Irina dirige le projet INCITE du ministère américain de l'Environnement au sujet des modèles de fondation évolutifs sur les superordinateurs Summit et Frontier à l'Oak Ridge Leadership Computing Facility (OLCF). Elle est cofondatrice et directrice scientifique de Nolano.ai.

Ses recherches actuelles portent sur les lois de mise à l'échelle neuronale et les comportements émergents (capacités et alignement) dans les modèles de fondation, ainsi que sur l'apprentissage continu, la généralisation hors distribution et la robustesse. Avant de se joindre à l'UdeM en 2019, Irina était chercheuse au Centre de recherche IBM Thomas J. Watson, où elle a travaillé sur divers projets à l'intersection des neurosciences et de l'IA, et dirigé le défi NeuroAI. Elle a reçu plusieurs prix IBM : ceux de l’excellence et de l’innovation exceptionnelle (2018), celui de la réalisation technique exceptionnelle (2017), et celui de l’accomplissement en recherche (2009). Elle détient 64 brevets et a écrit plus de 120 articles de recherche, plusieurs chapitres de livres, trois livres publiés et une monographie sur la modélisation éparse.

Étudiants actuels

George Adamopoulos

Stagiaire de recherche

Ivan Anokhin

Doctorat - UdeM

Co-superviseur⋅e :

Samira Ebrahimi Kahou

Doctorat - UdeM

Arjun Ashok

Doctorat - UdeM

Co-superviseur⋅e :

Maîtrise recherche - UdeM

Doctorat - UdeM

Co-superviseur⋅e :

Doctorat - Concordia

Superviseur⋅e principal⋅e :

Eugene Belilovsky

Mohammad Javad Darvishi Bayazi

Amin Darabi

Doctorat - UdeM

Collaborateur·rice de recherche - UdeM

Wagner Drew

Maîtrise recherche - Concordia

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Collaborateur·rice de recherche

Co-superviseur⋅e :

Sarath Chandar

Parviz Haggi Mani

Visiteur de recherche indépendant - -

Nadhir Hassen

Collaborateur·rice de recherche - UdeM

Maîtrise recherche

Collaborateur·rice alumni - UdeM

Superviseur⋅e principal⋅e :

Ioannis Mitliagkas

Nizar Islah

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Doctorat - UdeM

Maîtrise recherche - Concordia

Superviseur⋅e principal⋅e :

Collaborateur·rice de recherche - UdeM

Neeraj Kumar

Collaborateur·rice alumni - UdeM

Gwen Legate

Doctorat - Concordia

Superviseur⋅e principal⋅e :

Eugene Belilovsky

David Lemay

Maîtrise recherche - UdeM

Amin Mansouri

Collaborateur·rice alumni - UdeM

Collaborateur·rice de recherche

Doctorat - UdeM

Collaborateur·rice de recherche - UdeM

Gabriela Moisescu-Pareja

Collaborateur·rice de recherche - McGill

Superviseur⋅e principal⋅e :

Doina Precup

Timothy Nest

Doctorat - UdeM

Co-superviseur⋅e :

Eilif B. Muller

Mohammad Pezeshki

Collaborateur·rice de recherche

Co-superviseur⋅e :

Collaborateur·rice de recherche - Polytechnique

Motahareh Pourrahimi

Doctorat - McGill

Superviseur⋅e principal⋅e :

Pouya Bashivan

Mahta Ramezanian

Maîtrise recherche - UdeM

Co-superviseur⋅e :

Guillaume Dumas

Matthew Riemer

Doctorat - UdeM

Alexis Roger

Doctorat - McGill

Superviseur⋅e principal⋅e :

Blake Richards

Munish Sathish Kumar

Collaborateur·rice de recherche

Vaibhav Singh

Doctorat - Concordia

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Doctorat - UdeM

Co-superviseur⋅e :

Collaborateur·rice alumni - UdeM

Sihui Wei

Baccalauréat - McGill

Andrew Williams

Doctorat - UdeM

Co-superviseur⋅e :

Maîtrise recherche - UdeM

He Zhu

Doctorat - McGill

Publications

Survey on Applications of Multi-Armed and Contextual Bandits

Djallel Bouneffouf

Charu Aggarwal

In recent years, the multi-armed bandit (MAB) framework has attracted a lot of attention in various applications, from recommender systems a… (voir plus)nd information retrieval to healthcare and finance. This success is due to its stellar performance combined with attractive properties, such as learning from less feedback. The multiarmed bandit field is currently experiencing a renaissance, as novel problem settings and algorithms motivated by various practical applications are being introduced, building on top of the classical bandit problem. This article aims to provide a comprehensive review of top recent developments in multiple real-life applications of the multi-armed bandit. Specifically, we introduce a taxonomy of common MAB-based applications and summarize the state-of-the-art for each of those domains. Furthermore, we identify important current trends and provide new perspectives pertaining to the future of this burgeoning field.

2020-07-18

2020 IEEE Congress on Evolutionary Computation (CEC) (publié)

Chaotic Continual Learning

Touraj Laleh

Mojtaba Faramarzi

A. Chandar

Training a deep neural network requires the model to go over training data for several epochs and update network parameters. In continual le… (voir plus)arning, this process results in catastrophic forgetting which is one of the core issues of this domain. Most proposed approaches for this issue try to compensate for the effects of parameter updates in the batch incremental setup in which the training model visits a lot of samples for several epochs. However, it is not realistic to expect training data will always be fed to model in a batch incremental setup. This paper proposes a chaotic stream learner that mimics the chaotic behavior of biological neurons and does not updates network parameters. In addition, it can work with fewer samples compared to deep learning models on stream learning setup. Our experiments on MNIST, CIFAR10, and Omniglot show that the chaotic stream learner has less catastrophic forgetting by its nature in comparison to a CNN model in continual learning.

2020-07-12

ICML.cc/2020/Workshop/LifelongML (inconnu)

openreview.net

An Empirical Study of Human Behavioral Agents in Bandits, Contextual Bandits and Reinforcement Learning.

Guillermo Cecchi

Djallel Bouneffouf

Jenna Reinen

Artificial behavioral agents are often evaluated based on their consistent behaviors and performance to take sequential actions in an enviro… (voir plus)nment to maximize some notion of cumulative reward. However, human decision making in real life usually involves different strategies and behavioral trajectories that lead to the same empirical outcome. Motivated by clinical literature of a wide range of neurological and psychiatric disorders, we propose here a more general and flexible parametric framework for sequential decision making that involves a two-stream reward processing mechanism. We demonstrated that this framework is flexible and unified enough to incorporate a family of problems spanning multi-armed bandits (MAB), contextual bandits (CB) and reinforcement learning (RL), which decompose the sequential decision making process in different levels. Inspired by the known reward processing abnormalities of many mental disorders, our clinically-inspired agents demonstrated interesting behavioral trajectories and comparable performance on simulated tasks with particular reward distributions, a real-world dataset capturing human decision-making in gambling tasks, and the PacMan game across different reward stationarities in a lifelong learning setting.

2020-05-09

(publié)

www.semanticscholar.org

Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL

Guillermo Cecchi

Djallel Bouneffouf

Jenna Reinen

2020-05-09

ArXiv (prépublication)

Modeling Dialogues with Hashcode Representations: A Nonparametric Approach

Sahil Garg

Guillermo Cecchi

Palash Goyal

Shuyang Gao

Sarik Ghazarian

Greg Ver Steeg

Aram Galstyan

We propose a novel dialogue modeling framework, the first-ever nonparametric kernel functions based approach for dialogue modeling, which le… (voir plus)arns hashcodes as text representations; unlike traditional deep learning models, it handles well relatively small datasets, while also scaling to large ones. We also derive a novel lower bound on mutual information, used as a model-selection criterion favoring representations with better alignment between the utterances of participants in a collaborative dialogue setting, as well as higher predictability of the generated responses. As demonstrated on three real-life datasets, including prominently psychotherapy sessions, the proposed approach significantly outperforms several state-of-art neural network based dialogue systems, both in terms of computational efficiency, reducing training time from days or weeks to hours, and the response quality, achieving an order of magnitude improvement over competitors in frequency of being chosen as the best model by human evaluators.

2020-04-02

AAAI Conference on Artificial Intelligence (publié)

Makesh Narsimhan Sreedhar

Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation

Victor Schmidt

Mostafa Elaraby

Unpaired Image-to-Image Translation (I2IT) tasks often suffer from lack of data, a problem which self-supervised learning (SSL) has recently… (voir plus) been very popular and successful at tackling. Leveraging auxiliary tasks such as rotation prediction or generative colorization, SSL can produce better and more robust representations in a low data regime. Training such tasks along an I2IT task is however computationally intractable as model size and the number of task grow. On the other hand, learning sequentially could incur catastrophic forgetting of previously learned tasks. To alleviate this, we introduce Lifelong Self-Supervision (LiSS) as a way to pre-train an I2IT model (e.g., CycleGAN) on a set of self-supervised auxiliary tasks. By keeping an exponential moving average of past encoders and distilling the accumulated knowledge, we are able to maintain the network's validation performance on a number of tasks without any form of replay, parameter isolation or retraining techniques typically used in continual learning. We show that models trained with LiSS perform better on past tasks, while also being more robust than the CycleGAN baseline to color bias and entity entanglement (when two entities are very close).

2020-03-30

ArXiv (prépublication)

Beyond Backprop: Different Approaches to Credit Assignment in Neural Nets

2020-03-04

(publié)

www.semanticscholar.org

Resting-state connectivity stratifies premanifest Huntington’s disease by longitudinal cognitive decline rate

Pablo Polosecki

Eduardo Castro

Dorian Pustina

John H. Warner

Andrew Wood

Cristina Sampaio

Guillermo Cecchi

2020-01-26

Scientific Reports (publié)

COVI White Paper - Version 1.1

Hannah Alsdurf

Yoshua Bengio

Tristan Deleu

Prateek Gupta

Daphne Ippolito

Richard Janda

Max Jarvies

Tyler Kolody

Sekoul Krastev

Tegan Maharaj

Robert Obryk

Dan Pilat

Nasim Rahaman

Jean-François Rousseau

Abhinav Sharma

Brooke Struck … (voir 3 de plus)

Jian Tang

Martin Weiss

Yun William Yu

The SARS-CoV-2 (Covid-19) pandemic has caused significant strain on public health institutions around the world. Contact tracing is an essen… (voir plus)tial tool to change the course of the Covid-19 pandemic. Manual contact tracing of Covid-19 cases has significant challenges that limit the ability of public health authorities to minimize community infections. Personalized peer-to-peer contact tracing through the use of mobile apps has the potential to shift the paradigm. Some countries have deployed centralized tracking systems, but more privacy-protecting decentralized systems offer much of the same benefit without concentrating data in the hands of a state authority or for-profit corporations. Machine learning methods can circumvent some of the limitations of standard digital tracing by incorporating many clues and their uncertainty into a more graded and precise estimation of infection risk. The estimated risk can provide early risk awareness, personalized recommendations and relevant information to the user. Finally, non-identifying risk data can inform epidemiological models trained jointly with the machine learning predictor. These models can provide statistical evidence for the importance of factors involved in disease transmission. They can also be used to monitor, evaluate and optimize health policy and (de)confinement scenarios according to medical and economic productivity indicators. However, such a strategy based on mobile apps and machine learning should proactively mitigate potential ethical and privacy risks, which could have substantial impacts on society (not only impacts on health but also impacts such as stigmatization and abuse of personal data). Here, we present an overview of the rationale, design, ethical considerations and privacy strategy of `COVI,' a Covid-19 public peer-to-peer contact tracing and risk awareness mobile application developed in Canada.

2019-12-31

arXiv (prépublication)

Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL

Guillermo Cecchi

Djallel Bouneffouf

Jenna Reinen

2019-12-31

HBAI@IJCAI (publié)

Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning

Massimo Caccia

Pau Rodríguez

Lucas Caccia

Alexandre Lacoste

Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent c… (voir plus)ontinual-learning scenarios have opened new avenues of research. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation. In their original formulations, both methods have limitations. We stand on their shoulders to propose a more general scenario, OSAKA, where an agent must quickly solve new (out-of-distribution) tasks, while also requiring fast remembering. We show that current continual learning, meta-learning, meta-continual learning, and continual-meta learning techniques fail in this new scenario. We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario. We empirically show that Continual-MAML is better suited to the new scenario than the aforementioned methodologies, as well as standard continual learning and meta-learning approaches.

2019-12-31

NeurIPS (publié)

A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry

Guillermo Cecchi

Djallel Bouneffouf

Jenna Reinen

Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework fo… (voir plus)r reinforcement learning that extends standard Q-learning to a two-stream model for processing positive and negative rewards, and allows to incorporate a wide range of reward-processing biases -- an important component of human decision making which can help us better understand a wide spectrum of multi-agent interactions in complex real-world socioeconomic systems, as well as various neuropsychiatric conditions associated with disruptions in normal reward processing. From the computational perspective, we observe that the proposed Split-QL model and its clinically inspired variants consistently outperform standard Q-Learning and SARSA methods, as well as recently proposed Double Q-Learning approaches, on simulated tasks with particular reward distributions, a real-world dataset capturing human decision-making in gambling tasks, and the Pac-Man game in a lifelong learning setting across different reward stationarities.

2019-12-31

AAMAS (publié)