Portrait de Irina Rish

Irina Rish

Membre académique principal
Chaire en IA Canada-CIFAR
Professeure titulaire, Université de Montréal, Département d'informatique et de recherche opérationnelle

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

Doctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Maîtrise recherche - Université de Montréal
Doctorat - Université de Montréal
Visiteur de recherche indépendant
Maîtrise recherche - Université de Montréal
Maîtrise recherche - Université de Montréal
Doctorat - Université de Montréal
Co-superviseur⋅e :
Collaborateur·rice de recherche
Doctorat - Université de Montréal
Co-superviseur⋅e :
Collaborateur·rice de recherche - Université de Montréal
Stagiaire de recherche - Technical University of Munich
Maîtrise recherche - Université de Montréal
Maîtrise recherche - Université de Montréal
Doctorat - McGill University
Superviseur⋅e principal⋅e :
Visiteur de recherche indépendant - Université de Montréal
Co-superviseur⋅e :
Doctorat - Concordia University
Superviseur⋅e principal⋅e :
Doctorat - Université de Montréal
Co-superviseur⋅e :
Collaborateur·rice alumni - Université de Montréal
Co-superviseur⋅e :
Maîtrise recherche - Université de Montréal
Co-superviseur⋅e :
Doctorat - Université de Montréal
Doctorat - Université de Montréal
Collaborateur·rice de recherche
Doctorat - Université de Montréal
Doctorat - McGill University
Superviseur⋅e principal⋅e :
Stagiaire de recherche - Université de Montréal
Maîtrise professionnelle - Université de Montréal
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Stagiaire de recherche - Université de Montréal
Collaborateur·rice de recherche - Politecnico di Milano
Doctorat - Université de Montréal
Co-superviseur⋅e :
Maîtrise recherche - Université de Montréal
Maîtrise recherche - Université de Montréal
Co-superviseur⋅e :
Maîtrise recherche - Université de Montréal
Collaborateur·rice de recherche - Université de Montréal
Doctorat - Université de Montréal
Maîtrise recherche - Université de Montréal
Maîtrise recherche - Université de Montréal
Doctorat - Université de Montréal
Co-superviseur⋅e :
Doctorat - Concordia University
Superviseur⋅e principal⋅e :
Postdoctorat - Université de Montréal
Superviseur⋅e principal⋅e :

Publications

Unsupervised Concept Discovery Mitigates Spurious Correlations
Md Rifat Arefin
Yan Zhang
Aristide Baratin
Francesco Locatello
Dianbo Liu
Kenji Kawaguchi
Deep Generative Sampling in the Dual Divergence Space: A Data-efficient&Interpretative Approach for Generative AI
Sahil Garg
Anderson Schneider
Anant Raj
Kashif Rasul
Yuriy Nevmyvaka
S. Gopal
Amit Dhurandhar
Guillermo A. Cecchi
Building on the remarkable achievements in generative sampling of natural images, we propose an innovative challenge, potentially overly amb… (voir plus)itious, which involves generating samples of entire multivariate time series that resemble images. However, the statistical challenge lies in the small sample size, sometimes consisting of a few hundred subjects. This issue is especially problematic for deep generative models that follow the conventional approach of generating samples from a canonical distribution and then decoding or denoising them to match the true data distribution. In contrast, our method is grounded in information theory and aims to implicitly characterize the distribution of images, particularly the (global and local) dependency structure between pixels. We achieve this by empirically estimating its KL-divergence in the dual form with respect to the respective marginal distribution. This enables us to perform generative sampling directly in the optimized 1-D dual divergence space. Specifically, in the dual space, training samples representing the data distribution are embedded in the form of various clusters between two end points. In theory, any sample embedded between those two end points is in-distribution w.r.t. the data distribution. Our key idea for generating novel samples of images is to interpolate between the clusters via a walk as per gradients of the dual function w.r.t. the data dimensions. In addition to the data efficiency gained from direct sampling, we propose an algorithm that offers a significant reduction in sample complexity for estimating the divergence of the data distribution with respect to the marginal distribution. We provide strong theoretical guarantees along with an extensive empirical evaluation using many real-world datasets from diverse domains, establishing the superiority of our approach w.r.t. state-of-the-art deep learning methods.
Simple and Scalable Strategies to Continually Pre-train Large Language Models
Adam Ibrahim
Benjamin Thérien
Kshitij Gupta
Mats Leon Richter
Quentin Anthony
Timothee LESORT
Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes ava… (voir plus)ilable. A much more efficient solution is to continually pre-train these models, saving significant compute compared to re-training. However, the distribution shift induced by new data typically results in degraded performance on previous data or poor adaptation to the new data. In this work, we show that a simple and scalable combination of learning rate (LR) re-warming, LR re-decaying, and replay of previous data is sufficient to match the performance of fully re-training from scratch on all available data, as measured by the final loss and the average score on several language model (LM) evaluation benchmarks. Specifically, we show this for a weak but realistic distribution shift between two commonly used LLM pre-training datasets (English
Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok
Tikeng Notsawo Pascal Junior
Pascal Notsawo
Hattie Zhou
Mohammad Pezeshki
Effective Latent Differential Equation Models via Attention and Multiple Shooting
Germán Abrevaya
Mahta Ramezanian-Panahi
Jean-Christophe Gagnon-Audet
Pablo Polosecki
Silvina Ponce Dawson
Guillermo Cecchi
Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning
Mohammad-Javad Darvishi-Bayazi
Mohammad S. Ghaemi
Timothee LESORT
Md Rifat Arefin
Jocelyn Faubert
Towards Machines that Trust: AI Agents Learn to Trust in the Trust Game
Ardavan S. Nobandegani
Thomas Shultz
Widely considered a cornerstone of human morality, trust shapes many aspects of human social interactions. In this work, we present a theore… (voir plus)tical analysis of the
Challenging Common Assumptions about Catastrophic Forgetting and Knowledge Accumulation
Timothee LESORT
Oleksiy Ostapenko
Pau Rodriguez
Diganta Misra
Md Rifat Arefin
Lag-Llama: Towards Foundation Models for Time Series Forecasting
Kashif Rasul
Arjun Ashok
Andrew Robert Williams
Arian Khorasani
George Adamopoulos
Rishika Bhagwatkar
Marin Biloš
Hena Ghonia
Nadhir Hassen
Anderson Schneider
Sahil Garg
Yuriy Nevmyvaka
Aiming to build foundation models for time-series forecasting and study their scaling behavior, we present here our work-in-progress on Lag-… (voir plus)Llama, a general-purpose univariate probabilistic time-series forecasting model trained on a large collection of time-series data. The model shows good zero-shot prediction capabilities on unseen "out-of-distribution" time-series datasets, outperforming supervised baselines. We use smoothly broken power-laws to fit and predict model scaling behavior. The open source code is made available at https://github.com/kashif/pytorch-transformer-ts.
Gradient Masked Averaging for Federated Learning
Irene Tenison
Sai Aravind Sreeramadas
Vaikkunth Mugunthan
Edouard Oyallon
Federated learning (FL) is an emerging paradigm that permits a large number of clients with heterogeneous data to coordinate learning of a u… (voir plus)nified global model without the need to share data amongst each other. A major challenge in federated learning is the heterogeneity of data across client, which can degrade the performance of standard FL algorithms. Standard FL algorithms involve averaging of model parameters or gradient updates to approximate the global model at the server. However, we argue that in heterogeneous settings, averaging can result in information loss and lead to poor generalization due to the bias induced by dominant client gradients. We hypothesize that to generalize better across non-i.i.d datasets, the algorithms should focus on learning the invariant mechanism that is constant while ignoring spurious mechanisms that differ across clients. Inspired from recent works in Out-of-Distribution generalization, we propose a gradient masked averaging approach for FL as an alternative to the standard averaging of client updates. This aggregation technique for client updates can be adapted as a drop-in replacement in most existing federated algorithms. We perform extensive experiments on multiple FL algorithms with in-distribution, real-world, feature-skewed out-of-distribution, and quantity imbalanced datasets and show that it provides consistent improvements, particularly in the case of heterogeneous clients.
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Kashif Rasul
Arjun Ashok
Andrew Robert Williams
Arian Khorasani
George Adamopoulos
Rishika Bhagwatkar
Marin Bilovs
Hena Ghonia
Nadhir Hassen
Anderson Schneider
Sahil Garg
Yuriy Nevmyvaka
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Kashif Rasul
Arjun Ashok
Andrew Robert Williams
Arian Khorasani
George Adamopoulos
Rishika Bhagwatkar
Marin Bilovs
Hena Ghonia
N. Hassen
Anderson Schneider
Sahil Garg
Yuriy Nevmyvaka
Over the past years, foundation models have caused a paradigm shift in machine learning due to their unprecedented capabilities for zero-sho… (voir plus)t and few-shot generalization. However, despite the success of foundation models in modalities such as natural language processing and computer vision, the development of foundation models for time series forecasting has lagged behind. We present Lag-Llama, a general-purpose foundation model for univariate probabilistic time series forecasting based on a decoder-only transformer architecture that uses lags as covariates. Lag-Llama is pretrained on a large corpus of diverse time series data from several domains, and demonstrates strong zero-shot generalization capabilities compared to a wide range of forecasting models on downstream datasets across domains. Moreover, when fine-tuned on relatively small fractions of such previously unseen datasets, Lag-Llama achieves state-of-the-art performance, outperforming prior deep learning approaches, emerging as the best general-purpose model on average. Lag-Llama serves as a strong contender to the current state-of-art in time series forecasting and paves the way for future advancements in foundation models tailored to time series data.