Aaron Courville

Alan Alan

PhD - Université de Montréal

Principal supervisor :

PhD - Université de Montréal

Principal supervisor :

Laurent Charlin

Juan Duque

PhD - Université de Montréal

PhD - Université de Montréal

Arian Hosseini

PhD - Université de Montréal

Uday Kapur

PhD - Université de Montréal

Amr Khalifa

PhD - Université de Montréal

Samuel Lavoie

PhD - Université de Montréal

Zhixuan Lin

PhD - Université de Montréal

PhD - Université de Montréal

Principal supervisor :

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Rishabh Agarwal

Andrei Nicolicioiu

PhD - Université de Montréal

Michael Noukhovitch

PhD - Université de Montréal

Johan Samir Obando Ceron

PhD - Université de Montréal

Co-supervisor :

Collaborating researcher - Université de Montréal

Dereck Piché

PhD - Université de Montréal

Khaled Rouissi

Master's Research - Université de Montréal

Esra'a Saleh

PhD - Université de Montréal

Principal supervisor :

Glen Berseth

Vedant Shah

PhD - Université de Montréal

PhD - Université de Montréal

Yusong Wu

PhD - Université de Montréal

Principal supervisor :

Anna (Cheng-Zhi) Huang

Sujin yun

PhD - Université de Montréal

Xiaofeng Zhang

PhD - Université de Montréal

Publications

Unifying Likelihood-free Inference with Black-box Sequence Design and Beyond

2020-12-31

arXiv.org (preprint)

dblp.uni-trier.de

A Variational Perspective on Diffusion-Based Generative Models and Score Matching

Jae Hyun Lim

Discrete-time diffusion-based generative models and score matching methods have shown promising results in modeling high-dimensional image d… (see more)ata. Recently, Song et al. (2021) show that diffusion processes that transform data into noise can be reversed via learning the score function, i.e. the gradient of the log-density of the perturbed data. They propose to plug the learned score function into an inverse formula to define a generative diffusion process. Despite the empirical success, a theoretical underpinning of this procedure is still lacking. In this work, we approach the (continuous-time) generative diffusion directly and derive a variational framework for likelihood estimation, which includes continuous-time normalizing flows as a special case, and can be seen as an infinitely deep variational autoencoder. Under this framework, we show that minimizing the score-matching loss is equivalent to maximizing a lower bound of the likelihood of the plug-in reverse SDE proposed by Song et al. (2021), bridging the theoretical gap.

2020-12-31

Advances in Neural Information Processing Systems 34 (NeurIPS 2021) (published)

openreview.net

Bijective-Contrastive Estimation

Jae Hyun Lim

Christopher Pal

In this work, we propose Bijective-Contrastive Estimation (BCE), a classification-based learning criterion for energy-based models. We gener… (see more)ate a collection of contrasting distributions using bijections, and solve all the classification problems between the original data distribution and the distributions induced by the bijections using a classifier parameterized by an energy model. We show that if the classification objective is minimized, the energy function will uniquely recover the data density up to a normalizing constant. This has the benefit of not having to explicitly specify a contrasting distribution, like noise contrastive estimation. Experimentally, we demonstrate that the proposed method works well on 2D synthetic datasets. We discuss the difficulty in high dimensional cases, and propose potential directions to explore for future work.

2020-12-20

Symposium on Advances in Approximate Bayesian Inference (accepted)

openreview.net

AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation

Jae Hyun Lim

Christopher Pal

Entropy is ubiquitous in machine learning, but it is in general intractable to compute the entropy of the distribution of an arbitrary conti… (see more)nuous random variable. In this paper, we propose the amortized residual denoising autoencoder (AR-DAE) to approximate the gradient of the log density function, which can be used to estimate the gradient of entropy. Amortization allows us to significantly reduce the error of the gradient approximator by approaching asymptotic optimality of a regular DAE, in which case the estimation is in theory unbiased. We conduct theoretical and experimental analyses on the approximation error of the proposed method, as well as extensive studies on heuristics to ensure its robustness. Finally, using the proposed gradient approximator to estimate the gradient of entropy, we demonstrate state-of-the-art performance on density estimation with variational autoencoders and continuous control with soft actor-critic.

2020-11-20

Proceedings of the 37th International Conference on Machine Learning (published)

proceedings.mlr.press

Countering Language Drift with Seeded Iterated Learning

Yuchen Lu

Soumye Singhal

Florian Strub

Olivier Pietquin

Pretraining on human corpus and then finetuning in a simulator has become a standard pipeline for training a goal-oriented dialogue agent. N… (see more)evertheless, as soon as the agents are finetuned to maximize task completion, they suffer from the so-called language drift phenomenon: they slowly lose syntactic and semantic properties of language as they only focus on solving the task. In this paper, we propose a generic approach to counter language drift called Seeded iterated learning (SIL). We periodically refine a pretrained student agent by imitating data sampled from a newly generated teacher agent. At each time step, the teacher is created by copying the student agent, before being finetuned to maximize task completion. SIL does not require external syntactic constraint nor semantic knowledge, making it a valuable task-agnostic finetuning protocol. We evaluate SIL in a toy-setting Lewis Game, and then scale it up to the translation game with natural language. In both settings, SIL helps counter language drift as well as it improves the task completion compared to baselines.

2020-11-20

Proceedings of the 37th International Conference on Machine Learning (published)

proceedings.mlr.press

Recursive Top-Down Production for Sentence Generation with Latent Trees

Timothy J. O'Donnell

We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic p… (see more)rogramming algorithm that marginalises over latent binary tree structures with

2020-10-31

Findings of the Association for Computational Linguistics: EMNLP 2020 (published)

Supervised Seeded Iterated Learning for Interactive Language Learning

Yuchen Lu

Soumye Singhal

Florian Strub

Olivier Pietquin

2020-10-31

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (published)

NU-GAN: High resolution neural upsampling with GAN

In this paper, we propose NU-GAN, a new method for resampling audio from lower to higher sampling rates (upsampling). Audio upsampling is an… (see more) important problem since productionizing generative speech technology requires operating at high sampling rates. Such applications use audio at a resolution of 44.1 kHz or 48 kHz, whereas current speech synthesis methods are equipped to handle a maximum of 24 kHz resolution. NU-GAN takes a leap towards solving audio upsampling as a separate component in the text-to-speech (TTS) pipeline by leveraging techniques for audio generation using GANs. ABX preference tests indicate that our NU-GAN resampler is capable of resampling 22 kHz to 44.1 kHz audio that is distinguishable from original audio only 7.4% higher than random chance for single speaker dataset, and 10.8% higher than chance for multi-speaker dataset.

2020-10-21

arXiv (preprint)

Explicitly Modeling Syntax in Language Model improves Generalization

Syntax is fundamental to our thinking about language. Although neural networks are very successful in many tasks, they do not explicitly mod… (see more)el syntactic structure. Failing to capture the structure of inputs could lead to generalization problems and over-parametrization. In the present work, we propose a new syntax-aware language model: Syntactic Ordered Memory (SOM). The model explicitly models the structure with a one-step look-ahead parser and maintains the conditional probability setting of the standard language model. Experiments show that SOM can achieve strong results in language modeling and syntactic generalization tests, while using fewer parameters then other models.

2020-10-20

arXiv.org (preprint)

dblp.uni-trier.de

A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM

Iulian V. Serban

Varun Gupta

Ekaterina Kochmar

Dung D. Vu

Robert Belfer

2020-06-09

Artificial Intelligence in Education (published)

Stochastic Neural Network with Kronecker Flow

Gintare Karolina Dziugaite

Ahmed Touati

Pascal Vincent

Alexandre Lacoste

Recent advances in variational inference enable the modelling of highly structured joint distributions, but are limited in their capacity to… (see more) scale to the high-dimensional setting of stochastic neural networks. This limitation motivates a need for scalable parameterizations of the noise generation process, in a manner that adequately captures the dependencies among the various parameters. In this work, we address this need and present the Kronecker Flow, a generalization of the Kronecker product to invertible mappings designed for stochastic neural networks. We apply our method to variational Bayesian neural networks on predictive tasks, PAC-Bayes generalization bound estimation, and approximate Thompson sampling in contextual bandits. In all setups, our methods prove to be competitive with existing methods and better than the baselines.

2020-06-02

Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)

proceedings.mlr.press

Detecting semantic anomalies

Faruk Ahmed

We critically appraise the recent interest in out-of-distribution (OOD) detection and question the practical relevance of existing benchmark… (see more)s. While the currently prevalent trend is to consider different datasets as OOD, we argue that out-distributions of practical interest are ones where the distinction is semantic in nature for a specified context, and that evaluative tasks should reflect this more closely. Assuming a context of object recognition, we recommend a set of benchmarks, motivated by practical applications. We make progress on these benchmarks by exploring a multi-task learning based approach, showing that auxiliary objectives for improved semantic awareness result in improved semantic anomaly detection, with accompanying generalization benefits.

2020-04-02

Proceedings of the AAAI Conference on Artificial Intelligence (published)