Irina Rish

sayed.mansouri-tehrani@mila.quebec

Amin Darabi

PhD - Université de Montréal

amin.darabi@mila.quebec

Amin Memarian

Independent visiting researcher

memariaa@mila.quebec

Amin Mansouri

Master's Research - Université de Montréal

andrew.williams@mila.quebec

Andrei Mircea Romascanu

PhD - Université de Montréal

PhD - Université de Montréal

arian.khorasani@mila.quebec

Arian Khorasani

Master's Research - Université de Montréal

arnav-kumar.jain@mila.quebec

Arjun Ashok

PhD

Co-supervisor :

Alexandre Drouin

arjun.ashok@mila.quebec

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Collaborating researcher

ayush.kaushal@mila.quebec

Benjamin Therien

PhD - Université de Montréal

Co-supervisor :

benjamin.therien@mila.quebec

Collaborating researcher - Université de Montréal

connor.brennan@mila.quebec

Daria Yasafova

Research Intern - Technical University of Munich

daria.yasafova@mila.quebec

Dave Whipps

Master's Research - Université de Montréal

whippsda@mila.quebec

diganta.misra@mila.quebec

Diganta Misra

Master's Research - Université de Montréal

Postdoctorate

Principal supervisor :

Nicolas Le Roux

ekaterina.lobacheva@mila.quebec

PhD - McGill University

Principal supervisor :

Blake Richards

ethan.caballero@mila.quebec

george.adamopoulos@mila.quebec

George Adamopoulos

Research Intern

gopeshh.subbaraj@mila.quebec

Germán Abrevaya

Independent visiting researcher - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Gwen Legate

PhD - Concordia University

Principal supervisor :

gwendolyne.legate@mila.quebec

Ivan Anokhin

PhD - Université de Montréal

Co-supervisor :

Samira Ebrahimi Kahou

ivan.anokhin@mila.quebec

juan.mayor-torres@mila.quebec

Juan Manuel Mayor-Torres

Collaborating researcher

Collaborating Alumni - Université de Montréal

Co-supervisor :

Sarath Chandar Anbil Parthipan

kshitij.gupta@mila.quebec

Mahta Ramezanian

Master's Research - Université de Montréal

Co-supervisor :

mahta.ramezanian@mila.quebec

Matthew Riemer

PhD - Université de Montréal

matthew.riemer@mila.quebec

Maximilian Puelma Touzel

Collaborating researcher

PhD - Université de Montréal

arefinmr@mila.quebec

Mohammad Pezeshki

Collaborating researcher

pezeshki@mila.quebec

Mohammad-Javad Darvishi Bayazi

PhD - Université de Montréal

mohammad-javad.darvishi-bayasi@mila.quebec

PhD - Université de Montréal

faramarm@mila.quebec

Motahareh Pourrahimi

PhD - McGill University

Principal supervisor :

Pouya Bashivan

motahareh.pourrahimi@mila.quebec

nadhir.hassen@mila.quebec

Nadhir Hassen

Research Intern - Université de Montréal

Neeraj Kumar

Professional Master's - Université de Montréal

neeraj.kumar@mila.quebec

Nizar Islah

PhD - Université de Montréal

Principal supervisor :

Eilif Benjamin Muller

nizar.islah@mila.quebec

paolo.cudrano@mila.quebec

Omar Younis

Research Intern - Université de Montréal

omar.younis@mila.quebec

Collaborating researcher - Politecnico di Milano

Pascal Tikeng Notsawo

PhD - Université de Montréal

Co-supervisor :

pascal.tikeng@mila.quebec

Collaborating researcher

prateek.humane@mila.quebec

Master's Research - Université de Montréal

remus.mocanu@mila.quebec

Reza Bayat

Master's Research - Université de Montréal

Co-supervisor :

Pouya Bashivan

reza.bayat@mila.quebec

rishika.bhagwatkar@mila.quebec

Rishika Bhagwatkar

Master's Research - Université de Montréal

Collaborating researcher - Université de Montréal

roland.riachi@mila.quebec

Simon Dufort-Labbé

PhD - Université de Montréal

simon.dufort-labbe@mila.quebec

Sparsha Mishra

Master's Research - Université de Montréal

sparsha.mishra@mila.quebec

Tejas Vaidhya

Master's Research - Université de Montréal

tejas.vaidhya@mila.quebec

PhD - Université de Montréal

Co-supervisor :

Eilif Benjamin Muller

timothy.nest@mila.quebec

Vaibhav Singh

PhD - Concordia University

Principal supervisor :

vaibhav.singh@mila.quebec

Zahra Sheikhbahaee

Postdoctorate - Université de Montréal

Principal supervisor :

zahra.sheikhbahaee@mila.quebec

Publications

Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers

Gabriele Prato

Simon Guiroy

Ethan Caballero

Sarath Chandar Anbil Parthipan

Empirical science of neural scaling laws is a rapidly growing area of significant importance to the future of machine learning, particularly… (see more) in the light of recent breakthroughs achieved by large-scale pre-trained models such as GPT-3, CLIP and DALL-e. Accurately predicting the neural network performance with increasing resources such as data, compute and model size provides a more comprehensive evaluation of different approaches across multiple scales, as opposed to traditional point-wise comparisons of fixed-size models on fixed-size benchmarks, and, most importantly, allows for focus on the best-scaling, and thus most promising in the future, approaches. In this work, we consider a challenging problem of few-shot learning in image classification, especially when the target data distribution in the few-shot phase is different from the source, training, data distribution, in a sense that it includes new image classes not encountered during training. Our current main goal is to investigate how the amount of pre-training data affects the few-shot generalization performance of standard image classifiers. Our key observations are that (1) such performance improvements are well-approximated by power laws (linear log-log plots) as the training set size increases, (2) this applies to both cases of target data coming from either the same or from a different domain (i.e., new classes) as the training data, and (3) few-shot performance on new classes converges at a faster rate than the standard classification performance on previously seen classes. Our findings shed new light on the relationship between scale and generalization.

2021-10-13

ArXiv (preprint)

openreview.net

Approximate Bayesian Optimisation for Neural Networks

Nadhir Hassen

2021-08-27

ArXiv (preprint)

Toward Optimal Solution for the Context-Attentive Bandit Problem

Djallel Bouneffouf

Raphael Feraud

Sohini Upadhyay

Yasaman Khazaeni

2021-08-19

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (published)

Sequoia: A Software Framework to Unify Continual Learning Research

Fabrice Normandin

Florian Golemo

Oleksiy Ostapenko

Pau Rodriguez

Matthew D Riemer

J. Hurtado

Lucas Cecchi

Khimya Khetarpal

Dominic Zhao

Ryan Lindeborg

Timothee LESORT

David Vazquez

Laurent Charlin

Massimo Caccia

The field of Continual Learning (CL) seeks to develop algorithms that accumulate knowledge and skills over time through interaction with non… (see more)-stationary environments. In practice, a plethora of evaluation procedures (settings) and algorithmic solutions (methods) exist, each with their own potentially disjoint set of assumptions. This variety makes measuring progress in CL difficult. We propose a taxonomy of settings, where each setting is described as a set of assumptions. A tree-shaped hierarchy emerges from this view, where more general settings become the parents of those with more restrictive assumptions. This makes it possible to use inheritance to share and reuse research, as developing a method for a given setting also makes it directly applicable onto any of its children. We instantiate this idea as a publicly available software framework called Sequoia, which features a wide variety of settings from both the Continual Supervised Learning (CSL) and Continual Reinforcement Learning (CRL) domains. Sequoia also includes a growing suite of methods which are easy to extend and customize, in addition to more specialized methods from external libraries. We hope that this new paradigm and its first implementation can help unify and accelerate research in CL. You can help us grow the tree by visiting (this GitHub URL).

2021-08-02

ArXiv (preprint)

openreview.net

Parametric Scattering Networks

Shanel Gauthier

Benjamin Th'erien

Laurent Alséne-Racicot

Michael Eickenberg

Guy Wolf

The wavelet scattering transform creates geometric in-variants and deformation stability. In multiple signal do-mains, it has been shown to … (see more)yield more discriminative rep-resentations compared to other non-learned representations and to outperform learned representations in certain tasks, particularly on limited labeled data and highly structured signals. The wavelet filters used in the scattering trans-form are typically selected to create a tight frame via a pa-rameterized mother wavelet. In this work, we investigate whether this standard wavelet filterbank construction is op-timal. Focusing on Morlet wavelets, we propose to learn the scales, orientations, and aspect ratios of the filters to produce problem-specific parameterizations of the scattering transform. We show that our learned versions of the scattering transform yield significant performance gains in small-sample classification settings over the standard scat-tering transform. Moreover, our empirical results suggest that traditional filterbank constructions may not always be necessary for scattering transforms to extract effective rep-resentations.

2021-07-20

ArXiv (preprint)

Double-Linear Thompson Sampling for Context-Attentive Bandits

Djallel Bouneffouf

Raphael Feraud

Sohini Upadhyay

Yasaman Khazaeni

In this paper, we analyze and extend an online learning frame-work known as Context-Attentive Bandit, motivated by various practical applica… (see more)tions, from medical diagnosis to dialog systems, where due to observation costs only a small subset of a potentially large number of context variables can be observed at each iteration; however, the agent has a freedom to choose which variables to observe. We derive a novel algorithm, called Context-Attentive Thompson Sampling (CATS), which builds upon the Linear Thompson Sampling approach, adapting it to Context-Attentive Bandit setting. We provide a theoretical regret analysis and an extensive empirical evaluation demonstrating advantages of the proposed approach over several baseline methods on a variety of real-life datasets.

2021-06-06

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (published)

Toward Skills Dialog Orchestration with Online Learning

Djallel Bouneffouf

Raphael Feraud

Sohini Upadhyay

Mayank Agarwal

Yasaman Khazaeni

Building multi-domain AI agents is a challenging task and an open problem in the area of AI. Within the domain of dialog, the ability to orc… (see more)hestrate multiple independently trained dialog agents, or skills, to create a unified system is of particular significance. In this work, we study the task of online posterior dialog orchestration, where we define posterior 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. To account for the various costs associated with extracting skill features, we consider online posterior orchestration under a skill execution budget. We formalize this setting as Context Attentive Bandit with Observations (CABO), a variant of context attentive bandits, and evaluate it on proprietary conversational datasets.

2021-06-06

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (published)

SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization

Soroosh Shahtalebi

Jean-Christophe Gagnon-Audet

Touraj Laleh

Mojtaba Faramarzi

Kartik Ahuja

A major bottleneck in the real-world applications of machine learning models is their failure in generalizing to unseen domains whose data d… (see more)istribution is not i.i.d to the training domains. This failure often stems from learning non-generalizable features in the training domains that are spuriously correlated with the label of data. To address this shortcoming, there has been a growing surge of interest in learning good explanations that are hard to vary, which is studied under the notion of Out-of-Distribution (OOD) Generalization. The search for good explanations that are \textit{invariant} across different domains can be seen as finding local (global) minimas in the loss landscape that hold true across all of the training domains. In this paper, we propose a masking strategy, which determines a continuous weight based on the agreement of gradients that flow in each edge of network, in order to control the amount of update received by the edge in each step of optimization. Particularly, our proposed technique referred to as"Smoothed-AND (SAND)-masking", not only validates the agreement in the direction of gradients but also promotes the agreement among their magnitudes to further ensure the discovery of invariances across training domains. SAND-mask is validated over the Domainbed benchmark for domain generalization and significantly improves the state-of-the-art accuracy on the Colored MNIST dataset while providing competitive results on other domain generalization datasets.

2021-06-04

ArXiv (preprint)

Continual Learning in Deep Networks: an Analysis of the Last Layer

Timothee LESORT

Thomas George

We study how different output layers in a deep neural network learn and forget in continual learning settings. The following three factors… (see more) can affect catastrophic forgetting in the output layer: (1) weights modifications, (2) interference, and (3) projection drift. In this paper, our goal is to provide more insights into how changing the output layers may address (1) and (2). Some potential solutions to those issues are proposed and evaluated here in several continual learning scenarios. We show that the best-performing type of the output layer depends on the data distribution drifts and/or the amount of data available. In particular, in some cases where a standard linear layer would fail, it turns out that changing parameterization is sufficient in order to achieve a significantly better performance, whithout introducing a continual-learning algorithm and instead using the standard SGD to train a model. Our analysis and results shed light on the dynamics of the output layer in continual learning scenarios, and suggest a way of selecting the best type of output layer for a given scenario.

2021-06-03

ArXiv (preprint)

openreview.net

Learning Brain Dynamics With Coupled Low-Dimensional Nonlinear Oscillators and Deep Recurrent Networks

Germán Abrevaya

Aleksandr Y. Aravkin

Peng Zheng

Jean-Christophe Gagnon-Audet

James Kozloski

Pablo Polosecki

Guillaume Lajoie

David Cox

Silvina Ponce Dawson

Guillermo Cecchi

Many natural systems, especially biological ones, exhibit complex multivariate nonlinear dynamical behaviors that can be hard to capture by … (see more)linear autoregressive models. On the other hand, generic nonlinear models such as deep recurrent neural networks often require large amounts of training data, not always available in domains such as brain imaging; also, they often lack interpretability. Domain knowledge about the types of dynamics typically observed in such systems, such as a certain type of dynamical systems models, could complement purely data-driven techniques by providing a good prior. In this work, we consider a class of ordinary differential equation (ODE) models known as van der Pol (VDP) oscil lators and evaluate their ability to capture a low-dimensional representation of neural activity measured by different brain imaging modalities, such as calcium imaging (CaI) and fMRI, in different living organisms: larval zebrafish, rat, and human. We develop a novel and efficient approach to the nontrivial problem of parameters estimation for a network of coupled dynamical systems from multivariate data and demonstrate that the resulting VDP models are both accurate and interpretable, as VDP's coupling matrix reveals anatomically meaningful excitatory and inhibitory interactions across different brain subsystems. VDP outperforms linear autoregressive models (VAR) in terms of both the data fit accuracy and the quality of insight provided by the coupling matrices and often tends to generalize better to unseen data when predicting future brain activity, being comparable to and sometimes better than the recurrent neural networks (LSTMs). Finally, we demonstrate that our (generative) VDP model can also serve as a data-augmentation tool leading to marked improvements in predictive accuracy of recurrent neural networks. Thus, our work contributes to both basic and applied dimensions of neuroimaging: gaining scientific insights and improving brain-based predictive models, an area of potentially high practical importance in clinical diagnosis and neurotechnology.

2021-05-26

Neural Computation (published)

Gradient Masked Federated Optimization

Irene Tenison

Sreya Francis

2021-04-21

ArXiv (preprint)

Towards Causal Federated Learning For Enhanced Robustness and Privacy

Sreya Francis

Irene Tenison

Federated Learning is an emerging privacy-preserving distributed machine learning approach to building a shared model by performing distribu… (see more)ted training locally on participating devices (clients) and aggregating the local models into a global one. As this approach prevents data collection and aggregation, it helps in reducing associated privacy risks to a great extent. However, the data samples across all participating clients are usually not independent and identically distributed (non-iid), and Out of Distribution(OOD) generalization for the learned models can be poor. Besides this challenge, federated learning also remains vulnerable to various attacks on security wherein a few malicious participating entities work towards inserting backdoors, degrading the generated aggregated model as well as inferring the data owned by participating entities. In this paper, we propose an approach for learning invariant (causal) features common to all participating clients in a federated learning setup and analyze empirically how it enhances the Out of Distribution (OOD) accuracy as well as the privacy of the final learned model.

2021-04-14

ArXiv (preprint)