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 - McGill University

Principal supervisor :

Blake Richards

Mohammad Javad Darvishi Bayazi

Amin Darabi

PhD - Université de Montréal

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Karim Jerbi

Wagner Drew

Master's Research - Concordia University

Principal supervisor :

Mirco Ravanelli

Mojtaba Faramarzi

PhD - Université de Montréal

Nadhir Hassen

Collaborating Alumni - 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

Jonathan Lim

Collaborating researcher

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

Timothy Nest

PhD - Université de Montréal

Co-supervisor :

Eilif Benjamin Muller

Mohammad Pezeshki

Collaborating researcher

Co-supervisor :

PhD - McGill University

Principal supervisor :

Pouya Bashivan

Mahta Ramezanian

Master's Research - Université de Montréal

Co-supervisor :

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 :

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

PhD - Université de Montréal

Co-supervisor :

Master's Research - Université de Montréal

Publications

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference

Matthew Riemer

Gopeshh Raaj Subbaraj

Glen Berseth

Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectivel… (see more)y minimize regret. However, recent advances in machine learning involve larger neural networks with longer inference times, raising questions about their applicability in realtime systems where reaction time is crucial. We present an analysis of lower bounds on regret in realtime reinforcement learning (RL) environments to show that minimizing long-term regret is generally impossible within the typical sequential interaction and learning paradigm, but often becomes possible when sufficient asynchronous compute is available. We propose novel algorithms for staggering asynchronous inference processes to ensure that actions are taken at consistent time intervals, and demonstrate that use of models with high action inference times is only constrained by the environment's effective stochasticity over the inference horizon, and not by action frequency. Our analysis shows that the number of inference processes needed scales linearly with increasing inference times while enabling use of models that are multiple orders of magnitude larger than existing approaches when learning from a realtime simulation of Game Boy games such as Pok\'emon and Tetris.

2024-12-18

ArXiv (preprint)

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching

Arnav Kumar Jain

Harley Wiltzer

Jesse Farebrother

Glen Berseth

Sanjiban Choudhury

In inverse reinforcement learning (IRL), an agent seeks to replicate expert demonstrations through interactions with the environment. Tradit… (see more)ionally, IRL is treated as an adversarial game, where an adversary searches over reward models, and a learner optimizes the reward through repeated RL procedures. This game-solving approach is both computationally expensive and difficult to stabilize. In this work, we propose a novel approach to IRL by direct policy optimization: exploiting a linear factorization of the return as the inner product of successor features and a reward vector, we design an IRL algorithm by policy gradient descent on the gap between the learner and expert features. Our non-adversarial method does not require learning a reward function and can be solved seamlessly with existing actor-critic RL algorithms. Remarkably, our approach works in state-only settings without expert action labels, a setting which behavior cloning (BC) cannot solve. Empirical results demonstrate that our method learns from as few as a single expert demonstration and achieves improved performance on various control tasks.

2024-11-11

ArXiv (preprint)

GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models

Nizar Islah

Justine Gehring

Diganta Misra

Eilif Muller

Terry Yue Zhuo

Massimo Caccia

2024-11-01

arXiv (published)

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Andrew Robert Williams

Arjun Ashok

Étienne Marcotte

Valentina Zantedeschi

Jithendaraa Subramanian

Roland Riachi

James Requeima

Alexandre Lacoste

Nicolas Chapados

Alexandre Drouin

Forecasting is a critical task in decision making across various domains. While numerical data provides a foundation, it often lacks crucial… (see more) context necessary for accurate predictions. Human forecasters frequently rely on additional information, such as background knowledge or constraints, which can be efficiently communicated through natural language. However, the ability of existing forecasting models to effectively integrate this textual information remains an open question. To address this, we introduce"Context is Key"(CiK), a time series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context, requiring models to integrate both modalities. We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters, and propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark. Our experiments highlight the importance of incorporating contextual information, demonstrate surprising performance when using LLM-based forecasting models, and also reveal some of their critical shortcomings. By presenting this benchmark, we aim to advance multimodal forecasting, promoting models that are both accurate and accessible to decision-makers with varied technical expertise. The benchmark can be visualized at https://servicenow.github.io/context-is-key-forecasting/v0/ .

2024-10-24

ArXiv (preprint)

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Andrew Robert Williams

Arjun Ashok

Étienne Marcotte

Valentina Zantedeschi

Jithendaraa Subramanian

Roland Riachi

James Requeima

Alexandre Lacoste

Nicolas Chapados

Alexandre Drouin

2024-10-24

ArXiv (preprint)

$\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers

Benjamin Thérien

Charles-Étienne Joseph

Boris Knyazev

Edouard Oyallon

Eugene Belilovsky

2024-10-10

NeurIPS.cc/2024/Workshop/OPT (published)

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Andrew Robert Williams

Arjun Ashok

Étienne Marcotte

Valentina Zantedeschi

Jithendaraa Subramanian

Roland Riachi

James Requeima

Alexandre Lacoste

Nicolas Chapados

Alexandre Drouin

2024-10-10

NeurIPS.cc/2024/Workshop/TSALM (published)

Introducing Brain Foundation Models

Mohammad Javad Darvishi Bayazi

Hena Ghonia

Roland Riachi

Bruno Aristimunha

Arian Khorasani

Md Rifat Arefin

Sylvain Chevallier

Amin Darabi

Brain function represents one of the most complex systems driving our world. Decoding its signals poses significant challenges, particularly… (see more) due to the limited availability of data and the high cost of recordings. The existence of large hospital datasets and laboratory collections partially mitigates this issue. However, the lack of standardized recording protocols, varying numbers of channels, diverse setups, scenarios, and recording devices further complicate the task. This work addresses these challenges by introducing the Brain Foundation Model (BFM), a suite of open-source models trained on brain signals. These models serve as foundational tools for various types of time-series neuroimaging tasks. This work presents the first model of the BFM series, which is trained on electroencephalogram signal data. Our results demonstrate that BFM-EEG can generate signals more accurately than other models. Upon acceptance, we will release the model weights and pipeline.

2024-10-10

NeurIPS.cc/2024/Workshop/TSALM (published)

Language model scaling laws and zero-sum learning

Andrei Mircea

Ekaterina Lobacheva

Supriyo Chakraborty

Nima Chitsazan

This work aims to understand how, in terms of training dynamics, scaling up language model size yields predictable loss improvements. We fin… (see more)d that these improvements can be tied back to loss deceleration, an abrupt transition in the rate of loss improvement, characterized by piece-wise linear behavior in log-log space. Notably, improvements from increased model size appear to be a result of (1) improving the loss at which this transition occurs; and (2) improving the rate of loss improvement after this transition. As an explanation for the mechanism underlying this transition (and the effect of model size on loss it mediates), we propose the zero-sum learning (ZSL) hypothesis. In ZSL, per-token gradients become systematically opposed, leading to degenerate training dynamics where the model can't improve loss on one token without harming it on another; bottlenecking the overall rate at which loss can improve. We find compelling evidence of ZSL, as well as unexpected results which shed light on other factors contributing to ZSL.

2024-10-10

NeurIPS.cc/2024/Workshop/SciForDL (poster)

LLMs and Personalities: Inconsistencies Across Scales

Tosato Tommaso

Mahmood Hegazy

David Lemay

Mohammed Abukalam

This study investigates the application of human psychometric assessments to large language models (LLMs) to examine their consistency and m… (see more)alleability in exhibiting personality traits. We administered the Big Five Inventory (BFI) and the Eysenck Personality Questionnaire-Revised (EPQ-R) to various LLMs across different model sizes and persona prompts. Our results reveal substantial variability in responses due to question order shuffling, challenging the notion of a stable LLM "personality." Larger models demonstrated more consistent responses, while persona prompts significantly influenced trait scores. Notably, the assistant persona led to more predictable scaling, with larger models exhibiting more socially desirable and less variable traits. In contrast, non-conventional personas displayed unpredictable behaviors, sometimes extending personality trait scores beyond the typical human range. These findings have important implications for understanding LLM behavior under different conditions and reflect on the consequences of scaling.

2024-10-09

NeurIPS.cc/2024/Workshop/Behavioral_ML (oral)

LLMs and Personalities: Inconsistencies Across Scales

Tosato Tommaso

Mahmood Hegazy

David Lemay

Mohammed Abukalam

2024-10-09

NeurIPS.cc/2024/Workshop/Behavioral_ML (oral)

RedPajama: an Open Dataset for Training Large Language Models

Maurice Weber

Daniel Y Fu

Quentin Gregory Anthony

Yonatan Oren

Shane Adams

Anton Alexandrov

Xiaozhong Lyu

Huu Nguyen

Xiaozhe Yao

Virginia Adams

Ben Athiwaratkun

Rahul Chalamala

Kezhen Chen

Max Ryabinin

Tri Dao

Percy Liang

Christopher Re

Ce Zhang

2024-09-26

NeurIPS.cc/2024/Datasets_and_Benchmarks_Track (spotlight)