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

George Adamopoulos

Research Intern

Ivan Anokhin

PhD - Université de Montréal

Co-supervisor :

Samira Ebrahimi Kahou

Rifat Arefin

PhD - Université de Montréal

Arjun Ashok

PhD - Université de Montréal

Co-supervisor :

Master's Research - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

PhD - Concordia University

Principal supervisor :

Mohammad Javad Darvishi Bayazi

Amin Darabi

PhD - Université de Montréal

Collaborating researcher - Université de Montréal

Wagner Drew

Master's Research - Concordia University

Principal supervisor :

Mirco Ravanelli

Mojtaba Faramarzi

PhD - Université de Montréal

Kshitij Gupta

Collaborating researcher

Co-supervisor :

Sarath Chandar

Parviz Haggi Mani

Independent visiting researcher - -

Nadhir Hassen

Collaborating researcher - Université de Montréal

Master's Research

Collaborating Alumni - Université de Montréal

Principal supervisor :

Ioannis Mitliagkas

Nizar Islah

PhD - Université de Montréal

Principal supervisor :

PhD - Université de Montréal

PhD - Université de Montréal

Zafir Khalid

Master's Research - Concordia University

Principal supervisor :

Collaborating researcher - Université de Montréal

Neeraj Kumar

Collaborating Alumni - Université de Montréal

Gwen Legate

PhD - Concordia University

Principal supervisor :

David Lemay

Master's Research - Université de Montréal

Amin Mansouri

Collaborating Alumni - Université de Montréal

Collaborating researcher

Andrei Mircea

PhD - Université de Montréal

Collaborating researcher - Université de Montréal

Gabriela Moisescu-Pareja

Collaborating researcher - McGill University

Principal supervisor :

Doina Precup

Timothy Nest

PhD - Université de Montréal

Co-supervisor :

Eilif B. Muller

Mohammad Pezeshki

Collaborating researcher

Co-supervisor :

Collaborating researcher - Polytechnique Montréal

Motahareh Pourrahimi

PhD - McGill University

Principal supervisor :

Pouya Bashivan

Mahta Ramezanian

Master's Research - Université de Montréal

Co-supervisor :

Guillaume Dumas

Matthew Riemer

PhD - Université de Montréal

Alexis Roger

PhD - McGill University

Principal supervisor :

Blake Richards

Munish Sathish Kumar

Collaborating researcher

Vaibhav Singh

PhD - Concordia University

Principal supervisor :

Gopeshh Subbaraj

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Collaborating Alumni - Université de Montréal

Sihui Wei

Undergraduate - McGill University

Andrew Williams

PhD - Université de Montréal

Co-supervisor :

Master's Research - Université de Montréal

He Zhu

PhD - McGill University

Publications

Maximum State Entropy Exploration using Predecessor and Successor Representations

Animals have a developed ability to explore that aids them in important tasks such as locating food, exploring for shelter, and finding misp… (see more)laced items. These exploration skills necessarily track where they have been so that they can plan for finding items with relative efficiency. Contemporary exploration algorithms often learn a less efficient exploration strategy because they either condition only on the current state or simply rely on making random open-loop exploratory moves. In this work, we propose

2023-09-20

NeurIPS.cc/2023/Conference (poster)

Jean-christophe Gagnon-audet

WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series

Kartik Ahuja

Mohammad Javad Darvishi Bayazi

Pooneh Mousavi

Guillaume Dumas

2023-08-31

TMLR (accepted)

Beyond performance: the role of task demand, effort, and individual differences in ab initio pilots

Mohammad-Javad Darvishi-Bayazi

Andrew Law

Sergio Mejia Romero

Sion Jennings

Jocelyn Faubert

Aviation safety depends on the skill and expertise of pilots to meet the task demands of flying an aircraft in an effective and efficient ma… (see more)nner. During flight training, students may respond differently to imposed task demands based on individual differences in capacity, physiological arousal, and effort. To ensure that pilots achieve a common desired level of expertise, training programs should account for individual differences to optimize pilot performance. This study investigates the relationship between task performance and physiological correlates of effort in ab initio pilots. Twenty-four participants conducted a flight simulator task with three difficulty levels and were asked to rate their perceived demand and effort using the NASA TLX. We recorded heart rate, EEG brain activity, and pupil size to assess changes in the participants’ mental and physiological states across different task demands. We found that, despite group-level correlations between performance error and physiological responses, individual differences in physiological responses to task demands reflected different levels of participant effort and task efficiency. These findings suggest that physiological monitoring of student pilots might provide beneficial insights to flight instructors to optimize pilot training at the individual level.

2023-08-27

Scientific Reports (published)

Mohammad Javad Darvishi Bayazi

Neural efficiency in an aviation task with different levels of difficulty: Assessing different biometrics during a performance task

Andrew Law

Sergio Mejia Romero

Sion Jennings

Jocelyn Faubert

2023-07-31

Journal of Vision (published)

Cognitive Models as Simulators: Using Cognitive Models to Tap into Implicit Human Feedback

Ardavan S. Nobandegani

Thomas Shultz

2023-06-19

ICML.cc/2023/Workshop/ILHF (published)

Continual Pre-Training of Large Language Models: How to (re)warm your model?

Quentin Gregory Anthony

Timothee LESORT

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to restart the process over again once new data becomes a… (see more)vailable. A much cheaper and more efficient solution would be to enable the continual pre-training of these models, i.e. updating pre-trained models with new data instead of re-training them from scratch. However, the distribution shift induced by novel data typically results in degraded performance on past data. Taking a step towards efficient continual pre-training, in this work, we examine the effect of different warm-up strategies. Our hypothesis is that the learning rate must be re-increased to improve compute efficiency when training on a new dataset. We study the warmup phase of models pre-trained on the Pile (upstream data, 300B tokens) as we continue to pre-train on SlimPajama (downstream data, 297B tokens), following a linear warmup and cosine decay schedule. We conduct all experiments on the Pythia 410M language model architecture and evaluate performance through validation perplexity. We experiment with different pre-training checkpoints, various maximum learning rates, and various warmup lengths. Our results show that while rewarming models first increases the loss on upstream and downstream data, in the longer run it improves the downstream performance, outperforming models trained from scratch

2023-06-19

ICML.cc/2023/Workshop/ES-FoMO (poster)

Towards Out-of-Distribution Adversarial Robustness

Adam Ibrahim

Charles Guille-escuret

Ioannis Mitliagkas

David Krueger

Pouya Bashivan

Adversarial robustness continues to be a major challenge for deep learning. A core issue is that robustness to one type of attack often fail… (see more)s to transfer to other attacks. While prior work establishes a theoretical trade-off in robustness against different

2023-06-19

ICML.cc/2023/Workshop/AdvML-Frontiers (published)

Dialogue System with Missing Observation

Djallel Bouneffouf

Mayank Agarwal

Within the domain of dialogue, the ability to orchestrate multiple independently trained dialogue agents to create a unified system is of pa… (see more)rticular importance. Where we define orchestration as the task of selecting a subset of skills which most appropriately answer a user input using features extracted from both the user input and the individual skills. In this work, we study the task of online dialogue orchestration where the user feedback associated with the dialogue agent may not always be observed. In order to address the missing feedback setting, we propose to combine the attentive contextual bandit approach with an unsupervised learning mechanism such as clustering. By leveraging clustering to estimate missing reward, we are able to learn from each incoming event, even those with missing rewards. Promising empirical results are obtained on proprietary conversational datasets.

2023-06-03

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (published)

Estimating individual minimum calibration for deep-learning with predictive performance recovery: An example case of gait surface classification from wearable sensor gait data

Guillaume Lam

Philippe C. Dixon

2023-04-29

Journal of Biomechanics (unknown)

Towards ethical multimodal systems

Alexis Roger

Esma Aimeur

2023-04-25

ArXiv (preprint)

arxiv.org

A Survey on Compositional Generalization in Applications

Baihan Lin

Djallel Bouneffouf

2023-02-01

ArXiv (preprint)

arxiv.org

Broken Neural Scaling Laws

Ethan Caballero

Kshitij Gupta

David Krueger

We present a smoothly broken power law functional form (that we refer to as a Broken Neural Scaling Law (BNSL)) that accurately models &… (see more) extrapolates the scaling behaviors of deep neural networks (i.e. how the evaluation metric of interest varies as amount of compute used for training (or inference), number of model parameters, training dataset size, model input size, number of training steps, or upstream performance varies) for various architectures & for each of various tasks within a large & diverse set of upstream & downstream tasks, in zero-shot, prompted, & finetuned settings. This set includes large-scale vision, language, audio, video, diffusion, generative modeling, multimodal learning, contrastive learning, AI alignment, AI capabilities, robotics, out-of-distribution (OOD) generalization, continual learning, transfer learning, uncertainty estimation / calibration, OOD detection, adversarial robustness, distillation, sparsity, retrieval, quantization, pruning, fairness, molecules, computer programming/coding, math word problems, "emergent phase transitions", arithmetic, supervised learning, unsupervised/self-supervised learning, & reinforcement learning (single agent & multi-agent). When compared to other functional forms for neural scaling, this functional form yields extrapolations of scaling behavior that are considerably more accurate on this set. Moreover, this functional form accurately models & extrapolates scaling behavior that other functional forms are incapable of expressing such as the nonmonotonic transitions present in the scaling behavior of phenomena such as double descent & the delayed, sharp inflection points present in the scaling behavior of tasks such as arithmetic. Lastly, we use this functional form to glean insights about the limit of the predictability of scaling behavior. Code is available at https://github.com/ethancaballero/broken_neural_scaling_laws

2023-01-31

ICLR.cc/2023/Conference (poster)