Portrait of Eugene Belilovsky is unavailable

Eugene Belilovsky

Associate Academic Member

Assistant Professor, Concordia University, Department of Computer Science and Software Engineering

Adjunct Professor, Université de Montréal, Department of Computer Science and Operations Research

Biography

Eugene Belilovsky is an assistant professor in the Department of Computer Science and Software Engineering at Concordia University.

He is also an associate academic member of Mila – Quebec Artificial Intelligence Institute and an adjunct professor at Université de Montréal.

Belilovsky’s research specialties lie in computer vision and deep learning. His current interests include continual learning and few-shot learning, along with applications of these aspects at the intersection of computer vision and language processing.

Current Students

Abhinav Moudgil

PhD - Concordia University

abhinav.moudgil@mila.quebec

PhD - Concordia University

adel.nabli@mila.quebec

Albert Orozco Camacho

PhD - Concordia University

Co-supervisor :

orozcoca@mila.quebec

Alex Fulleringer

Master's Research - Concordia University

alexander.fulleringer@mila.quebec

AmirHossein Zamani

PhD - Concordia University

amirhossein.zamani@mila.quebec

Benjamin Therien

PhD - Université de Montréal

Principal supervisor :

benjamin.therien@mila.quebec

Charles-Etienne Joseph

Master's Research - Université de Montréal

Co-supervisor :

charles-etienne.joseph@mila.quebec

Master's Research - Concordia University

congshu.zou@mila.quebec

Collaborating researcher - Concordia University

Co-supervisor :

donald.shenaj@mila.quebec

Geraldin Nanfack

Postdoctorate - Concordia University

Co-supervisor :

geraldin.nanfack@mila.quebec

PhD - Concordia University

Co-supervisor :

gwendolyne.legate@mila.quebec

Humza Wajid Hameed

Master's Research - Concordia University

humza.wajid@mila.quebec

Research Intern - Concordia University

louis.fournier@mila.quebec

Master's Research - Concordia University

Co-supervisor :

paria.mehrbod@mila.quebec

PhD - Concordia University

mohammadreza.davari@mila.quebec

Collaborating Alumni

Co-supervisor :

nader.asadi@mila.quebec

Nicolas Bernier

Master's Research - Concordia University

nicolas.bernier@mila.quebec

Master's Research - Concordia University

paul.janson@mila.quebec

Collaborating researcher - Université de Montréal

Principal supervisor :

pedro.vianna@mila.quebec

PhD - Concordia University

Co-supervisor :

vaibhav.singh@mila.quebec

Master's Research - Concordia University

zafir.khaled@mila.quebec

Publications

Online Continual Learning with Maximally Interfered Retrieval

Rahaf Aljundi

Lucas Caccia

Eugene Belilovsky

Massimo Caccia

Min Lin

Laurent Charlin

Tinne Tuytelaars

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for mo… (see more)dern machine learning systems. In particular the online or "single-pass through the data" setting has gained attention recently as a natural setting that is difficult to tackle. Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks. These approaches typically rely on randomly selecting samples from the replay memory or from a generative model, which is suboptimal. In this work, we consider a controlled sampling of memories for replay. We retrieve the samples which are most interfered, i.e. whose prediction will be most negatively impacted by the foreseen parameters update. We show a formulation for this sampling criterion in both the generative replay and the experience replay setting, producing consistent gains in performance and greatly reduced forgetting. We release an implementation of our method at this https URL.

2019-08-11

ArXiv (preprint)

Learning Optimizers for Local SGD

Charles-Étienne Joseph

Benjamin Thérien

Abhinav Moudgil

Boris Knyazev

Eugene Belilovsky

Communication-efficient variants of SGD, specifically local SGD, have received a great deal of interest in recent years. These approaches co… (see more)mpute multiple gradient steps locally, that is on each worker, before averaging model parameters, helping relieve the critical communication bottleneck in distributed deep learning training. Although many variants of these approaches have been proposed, they can sometimes lag behind state-of-the-art optimizers for deep learning. In this work, we incorporate local optimizers that compute multiple updates into a learned optimization framework, allowing to meta-learn potentially more efficient local SGD algorithms. Our results demonstrate that local learned optimizers can substantially outperform local SGD and its sophisticated variants while maintaining their communication efficiency. We show that the learned optimizers can generalize to new datasets and architectures, demonstrating the potential of learned optimizers for improving communication-efficient distributed learning.

2000-01-01

(published)

www.semanticscholar.org