Guillaume Rabusseau

Biography

I have been an assistant professor at Mila – Quebec Artificial Intelligence Institute and in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal (UdeM) since September 2018. I was awarded a Canada CIFAR AI Chair in March 2019. Before joining UdeM, I was a postdoctoral research fellow in the Reasoning and Learning Lab at McGill University, where I worked with Prakash Panangaden, Joelle Pineau and Doina Precup.

I obtained my PhD in 2016 from Aix-Marseille University (AMU) in France, where I worked in the Qarma team (Machine Learning and Multimedia) under the supervision of François Denis and Hachem Kadri. I also obtained my MSc in fundamental computer science and my BSc in computer science from AMU. I am interested in tensor methods for machine learning and in designing learning algorithms for structured data by leveraging linear and multilinear algebra (e.g., spectral methods).

Current Students

Jun Dai

Postdoctorate - Université de Montréal

Alireza Dizaji

Master's Research - Université de Montréal

Github

Marawan Gamal

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Collaborating Alumni - McGill University

Principal supervisor :

Collaborating researcher - Université de Montréal

Github

Maude Lizaire

PhD - Université de Montréal

Sitao Luan

Postdoctorate - McGill University

Co-supervisor :

Master's Research - Université de Montréal

Soroush Omranpour

Collaborating Alumni - McGill University

Principal supervisor :

Reihaneh Rabbany

Github

Michael Rizvi-Martel

PhD - Université de Montréal

Co-supervisor :

Pascal Tikeng Notsawo

PhD - Université de Montréal

Co-supervisor :

Collaborating researcher - Université de Montréal

Co-supervisor :

Reihaneh Rabbany

Website

Beheshteh Toloueirakhshan

PhD - Université de Montréal

Website

Publications

Few Shot Image Generation via Implicit Autoencoding of Support Sets

Andy Huang

Kuan-Chieh Wang

Alireza Makhzani

Recent generative models such as generative adversarial networks have achieved remarkable success in generating realistic images, but they r… (see more)equire large training datasets and computational resources. The goal of few-shot image generation is to learn the distribution of a new dataset from only a handful of examples by transferring knowledge learned from structurally similar datasets. Towards achieving this goal, we propose the “Implicit Support Set Autoencoder” (ISSA) that adversarially learns the relationship across datasets using an unsupervised dataset representation, while the distribution of each individual dataset is learned using implicit distributions. Given a few examples from a new dataset, ISSA can generate new samples by inferring the representation of the underlying distribution using a single forward pass. We showcase significant gains from our method on generating high quality and diverse images for unseen classes in the Omniglot and CelebA datasets in few-shot image generation settings.

2021-12-10

NeurIPS.cc/2021/Workshop/MetaLearn (poster)

openreview.net

Lower and Upper Bounds on the Pseudo-Dimension of Tensor Network Models

Behnoush Khavari

Tensor network (TN) methods have been a key ingredient of advances in condensed matter physics and have recently sparked interest in the mac… (see more)hine learning community for their ability to compactly represent very high-dimensional objects. TN methods can for example be used to efﬁciently learn linear models in exponentially large feature spaces [56]. In this work, we derive upper and lower bounds on the VC-dimension and pseudo-dimension of a large class of TN models for classiﬁcation, regression and completion. Our upper bounds hold for linear models parameterized by arbitrary TN structures, and we derive lower bounds for common tensor decomposition models (CP, Tensor Train, Tensor Ring and Tucker) showing the tightness of our general upper bound. These results are used to derive a generalization bound which can be applied to classiﬁcation with low-rank matrices as well as linear classiﬁers based on any of the commonly used tensor decomposition models. As a corollary of our results, we obtain a bound on the VC-dimension of the matrix product state classiﬁer introduced in [56] as a function of the so-called bond dimension (i.e. tensor train rank), which answers an open problem listed by Cirac, Garre-Rubio and Pérez-García in [13].

openreview.net

Rademacher Random Projections with Tensor Networks

Beheshteh T. Rakhshan

Random projection (RP) have recently emerged as popular techniques in the machine learning community for their ability in reducing the dimen… (see more)sion of very high-dimensional tensors. Following the work in [30], we consider a tensorized random projection relying on Tensor Train (TT) decomposition where each element of the core tensors is drawn from a Rademacher distribution. Our theoretical results reveal that the Gaussian low-rank tensor represented in compressed form in TT format in [30] can be replaced by a TT tensor with core elements drawn from a Rademacher distribution with the same embedding size. Experiments on synthetic data demonstrate that tensorized Rademacher RP can outperform the tensorized Gaussian RP studied in [30]. In addition, we show both theoretically and experimentally, that the tensorized RP in the Matrix Product Operator (MPO) format is not a Johnson-Lindenstrauss transform (JLT) and therefore not a well-suited random projection map

2021-10-26

ArXiv (preprint)

Extracting Weighted Automata for Approximate Minimization in Language Modelling

Clara Lacroce

Prakash Panangaden

2021-08-25

Proceedings of the Fifteenth International Conference on Grammatical Inference (published)

proceedings.mlr.press

Understanding Capacity Saturation in Incremental Learning

Shenyang Huang

Vincent Francois-Lavet

2021-06-08

Canadian Conference on AI (published)

doi.org

Quantum Tensor Networks, Stochastic Processes, and Weighted Automata

Siddarth Srinivasan

Sandesh M. Adhikary

Jacob Miller

Byron Boots

Modeling joint probability distributions over sequences has been studied from many perspectives. The physics community developed matrix prod… (see more)uct states, a tensor-train decomposition for probabilistic modeling, motivated by the need to tractably model many-body systems. But similar models have also been studied in the stochastic processes and weighted automata literature, with little work on how these bodies of work relate to each other. We address this gap by showing how stationary or uniform versions of popular quantum tensor network models have equivalent representations in the stochastic processes and weighted automata literature, in the limit of infinitely long sequences. We demonstrate several equivalence results between models used in these three communities: (i) uniform variants of matrix product states, Born machines and locally purified states from the quantum tensor networks literature, (ii) predictive state representations, hidden Markov models, norm-observable operator models and hidden quantum Markov models from the stochastic process literature,and (iii) stochastic weighted automata, probabilistic automata and quadratic automata from the formal languages literature. Such connections may open the door for results and methods developed in one area to be applied in another.

2021-03-18

Proceedings of The 24th International Conference on Artificial Intelligence and Statistics (published)

proceedings.mlr.press

Optimal Spectral-Norm Approximate Minimization of Weighted Finite Automata

Borja Balle

Clara Lacroce

Prakash Panangaden

Doina Precup

We address the approximate minimization problem for weighted finite automata (WFAs) with weights in …

2021-02-13

ArXiv (preprint)

doi.org

Assessing the Impact: Does an Improvement to a Revenue Management System Lead to an Improved Revenue?

Greta Laage

Emma Frejinger

Andrea Lodi

2021-01-13

ArXiv (preprint)

Estimating the Impact of an Improvement to a Revenue Management System: An Airline Application

Greta Laage

Emma Frejinger

William L. Hamilton

Andrea Lodi

Airlines have been making use of highly complex Revenue Management Systems to maximize revenue for decades. Estimating the impact of changin… (see more)g one component of those systems on an important outcome such as revenue is crucial, yet very challenging. It is indeed the difference between the generated value and the value that would have been generated keeping business as usual, which is not observable. We provide a comprehensive overview of counterfactual prediction models and use them in an extensive computational study based on data from Air Canada to estimate such impact. We focus on predicting the counterfactual revenue and compare it to the observed revenue subject to the impact. Our microeconomic application and small expected treatment impact stand out from the usual synthetic control applications. We present accurate linear and deep-learning counterfactual prediction models which achieve respectively 1.1% and 1% of error and allow to estimate a simulated effect quite accurately.

2021-01-01

arXiv.org (preprint)

dblp.uni-trier.de

Scalable Change Point Detection for Dynamic Graphs

Shenyang Huang

Reihaneh Rabbany

Real world networks often evolve in complex ways over time. Understanding anomalies in dynamic networks is crucial for applications such as … (see more)traffic accident detection, intrusion identification and detection of ecosystem disturbances. In this work, we focus on the problem of change point detection in dynamic graphs. The goal is to identify time steps where the graph structure deviates significantly from the norm. Despite empirical success of recent methods, building a change point detection method for real world dynamic graphs, which often scale to millions of nodes, remains an open question. To fill this gap, we propose LADdos, a scalable method for change point detection in dynamic graphs. LADdos brings together ideas from two recent works: an accurate change point detection method for graphs called LAD [10] which detects the changes in the full Laplacian spectrum of the graph in each timestamp, and the general framework of network density of states (DOS) [5] which models the distribution of the singular values through efficient approximation methods. In experiments with two common graph models –the Stochastic Block Model (SBM) and the Barabási-Albert (BA) model – we show that LADdos has equal performance to LAD, which is the current state-of-the-art, while being orders of magnitude faster. For instance, on a dynamic graph with total 21 million edges over 150 timestamps, LADdos achieves 100x speedup when compared to LAD.

A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix

Thang Doan

Mehdi Abbana Bennani

Bogdan Mazoure

Pierre Alquier

2021-01-01

AISTATS (published)

proceedings.mlr.press

Towards a Trace-Preserving Tensor Network Representation of Quantum Channels

Siddarth Srinivasan

Sandesh M. Adhikary

Jacob Miller

Bibek Pokharel