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

Pietro Cagnasso

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

Niklas Herbster

Research Intern - Université de Montréal

Co-supervisor :

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

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training

The ever-growing availability of unlabeled data presents both opportunities and challenges for training artificial intelligence systems. Whi… (see more)le self-supervised learning (SSL) has emerged as a powerful paradigm for extracting meaningful representations from vast amounts of unlabeled data, existing methods still struggle to adapt to the non-stationary, non-IID nature of real-world data streams without forgetting previously learned knowledge. Recent works have adopted a repeated cosine annealing schedule for large-scale continual pre-training; however, these schedules (1) inherently cause forgetting during the re-warming phase and (2) have not been systematically compared to existing continual SSL methods. In this work, we systematically compare the widely used cosine schedule with the recently proposed infinite learning rate schedule and empirically find the latter to be a more effective alternative. Our extensive empirical evaluation across diverse image and language datasets demonstrates that the infinite learning rate schedule consistently enhances continual pre-training performance compared to a repeated cosine decay without being restricted to a fixed iteration budget. For instance, in a small-scale MAE pre-training setup, it outperforms several strong baselines from the literature. We then scale up our experiments to larger MAE pre-training and autoregressive language model pre-training. Our results show that the infinite learning rate schedule remains effective at scale, surpassing repeated cosine decay for both MAE pre-training and zero-shot LM benchmarks.

2025-06-10

ICML.cc/2025/Workshop/ES-FoMo-III (published)

MuLoCo: Muon is a practical inner optimizer for DiLoCo

Benjamin Therien

Xiaolong Huang

2025-06-10

ICML.cc/2025/Workshop/ES-FoMo-III (published)

AIF-GEN: Open-Source Platform and Synthetic Dataset Suite for Reinforcement Learning on Large Language Models

Jacob Chmura

Shahrad Mohammadzadeh

Taz Scott-Talib

Nishanth Anand

2025-06-08

CODEML @ International Conference on Machine Learning (published)

Artificial Neural Networks for Magnetoencephalography: A review of an emerging field

Arthur Dehgan

Hamza Abdelhedi

Vanessa Hadid

Karim Jerbi CoCo Lab

Magnetoencephalography (MEG) is a cutting-edge neuroimaging technique that measures the intricate brain dynamics underlying cognitive proces… (see more)ses with an unparalleled combination of high temporal and spatial precision. MEG data analytics has always relied on advanced signal processing and mathematical and statistical tools for various tasks ranging from data cleaning to probing the signals' rich dynamics and estimating the neural sources underlying the surface-level recordings. Like in most domains, the surge in Artificial Intelligence (AI) has led to the increased use of Machine Learning (ML) methods for MEG data classification. More recently, an emerging trend in this field is using Artificial Neural Networks (ANNs) to address many MEG-related tasks. This review provides a comprehensive overview of how ANNs are being used with MEG data from three vantage points: First, we review work that employs ANNs for MEG signal classification, i.e., for brain decoding. Second, we report on work that has used ANNs as putative models of information processing in the human brain. Finally, we examine studies that use ANNs as techniques to tackle methodological questions in MEG, including artifact correction and source estimation. Furthermore, we assess the current strengths and limitations of using ANNs with MEG and discuss future challenges and opportunities in this field. Finally, by establishing a detailed portrait of the field and providing practical recommendations for the future, this review seeks to provide a helpful reference for both seasoned MEG researchers and newcomers to the field who are interested in using ANNs to enhance the exploration of the complex dynamics of the human brain with MEG.

2025-05-26

Journal of Neural Engineering (published)

arxiv.org

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

Arjun Ashok

Andrew R. Williams

Étienne Marcotte

Valentina Zantedeschi

Jithendaraa Subramanian

Alexandre Lacoste

Forecasting is a critical task in decision-making across numerous domains. While historical numerical data provide a start, they fail to con… (see more)vey the complete context for reliable and accurate predictions. Human forecasters frequently rely on additional information, such as background knowledge and constraints, which can efficiently be communicated through natural language. However, in spite of recent progress with LLM-based forecasters, their ability 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; crucially, every task in CiK requires understanding textual context to be solved successfully. 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. This benchmark aims to advance multimodal forecasting by 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/.

2025-04-30

International Conference on Machine Learning (poster)

proceedings.mlr.press

AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

Tianyu Zhang

Andrew Williams

Phillip Wozny

Kai-Hendrik Cohrs

Koen Ponse

Marco Jiralerspong

Soham Phade

Sunil Srinivasa

Lu Li

Yang Zhang

Prateek Gupta

Erman Acar

Yoshua Bengio

Stephan Zheng

Comprehensive global cooperation is essential to limit global temperature increases while continuing economic development, e.g., reducing se… (see more)vere inequality or achieving long-term economic growth. Achieving long-term cooperation on climate change mitigation with n strategic agents poses a complex game-theoretic problem. For example, agents may negotiate and reach climate agreements, but there is no central authority to enforce adherence to those agreements. Hence, it is critical to design negotiation and agreement frameworks that foster cooperation, allow all agents to meet their individual policy objectives, and incentivize long-term adherence. This is an interdisciplinary challenge that calls for collaboration between researchers in machine learning, economics, climate science, law, policy, ethics, and other fields. In particular, we argue that machine learning is a critical tool to address the complexity of this domain. To facilitate this research, here we introduce RICE-N, a multi-region integrated assessment model that simulates the global climate and economy, and which can be used to design and evaluate the strategic outcomes for different negotiation and agreement frameworks. We also describe how to use multi-agent reinforcement learning to train rational agents using RICE-N. This framework underpinsAI for Global Climate Cooperation, a working group collaboration and competition on climate negotiation and agreement design. Here, we invite the scientific community to design and evaluate their solutions using RICE-N, machine learning, economic intuition, and other domain knowledge. More information can be found on www.ai4climatecoop.org.

2025-04-30

International Conference on Machine Learning (poster)

proceedings.mlr.press

Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons

When training neural networks, dying neurons -- units becoming inactive or saturated -- are traditionally seen as harmful. This paper sheds … (see more)new light on this phenomenon. By exploring the impact of various hyperparameter configurations on dying neurons during training, we gather insights on how to improve upon sparse training approaches to pruning. We introduce Demon Pruning (DemP), a method that controls the proliferation of dead neurons through a combination of noise injection on active units and a one-cycle schedule regularization strategy, dynamically leading to network sparsity. Experiments on CIFAR-10 and ImageNet datasets demonstrate that DemP outperforms existing dense-to-sparse structured pruning methods, achieving better accuracy-sparsity tradeoffs and accelerating training by up to 3.56

2025-02-12

TMLR (accepted)

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference

Matthew D Riemer

Gopeshh 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 Pokémon and Tetris.

2025-01-21

ICLR.cc/2025/Conference (poster)

Handling Delay in Real-Time Reinforcement Learning

Ivan Anokin

Rishav Rishav

Matthew Riemer

Stephen Chung

Samira Ebrahimi Kahou

Real-time reinforcement learning (RL) introduces several challenges. First, policies are constrained to a fixed number of actions per second… (see more) due to hardware limitations. Second, the environment may change while the network is still computing an action, leading to observational delay. The first issue can partly be addressed with pipelining, leading to higher throughput and potentially better policies. However, the second issue remains: if each neuron operates in parallel with an execution time of

2025-01-21

International Conference on Learning Representations (poster)

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching

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.

2025-01-21

International Conference on Learning Representations (poster)

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

Md Rifat Arefin

Gopeshh Subbaraj

Nicolas Gontier

Yann Lecun

Ravid Shwartz-Ziv

Christopher Pal

Decoder-only Transformers often struggle with complex reasoning tasks, particularly arithmetic reasoning requiring multiple sequential opera… (see more)tions. In this work, we identify representation collapse in the model's intermediate layers as a key factor limiting their reasoning capabilities. To address this, we propose Sequential Variance-Covariance Regularization (Seq-VCR), which enhances the entropy of intermediate representations and prevents collapse. Combined with dummy pause tokens as substitutes for chain-of-thought (CoT) tokens, our method significantly improves performance in arithmetic reasoning problems. In the challenging

2025-01-21

ICLR.cc/2025/Conference (poster)

Surprising Effectiveness of pretraining Ternary Language Model at Scale

Ayush Kaushal

Tejas Vaidhya

Arnab Mondal

Tejas Pandey

Aaryan Bhagat

Rapid advancements in GPU computational power has outpaced memory capacity and bandwidth growth, creating bottlenecks in Large Language Mode… (see more)l (LLM) inference. Post-training quantization is the leading method for addressing memory-related bottlenecks in LLM inference, but it suffers from significant performance degradation below 4-bit precision. This paper addresses these challenges by investigating the pretraining of low-bitwidth models specifically Ternary Language Models (TriLMs) as an alternative to traditional floating-point models (FloatLMs) and their post-training quantized versions (QuantLMs). We present Spectra LLM suite, the first open suite of LLMs spanning multiple bit-widths, including FloatLMs, QuantLMs, and TriLMs, ranging from 99M to 3.9B parameters trained on 300B tokens. Our comprehensive evaluation demonstrates that TriLMs offer superior scaling behavior in terms of model size (in bits). Surprisingly, at scales exceeding one billion parameters, TriLMs consistently outperform their QuantLM and FloatLM counterparts for a given bit size across various benchmarks. Notably, the 3.9B parameter TriLM matches the performance of the FloatLM 3.9B across all benchmarks, despite having fewer bits than FloatLM 830M. Overall, this research provides valuable insights into the feasibility and scalability of low-bitwidth language models, paving the way for the development of more efficient LLMs.

2025-01-21

International Conference on Learning Representations (spotlight)