Publications

DATA-EFFICIENT REINFORCEMENT LEARNING
Nitarshan Rajkumar
Michael Noukhovitch
Ankesh Anand
Laurent Charlin
(Rex) Devon Hjelm
Philip Bachman
Aaron Courville
Data efficiency poses a major challenge for deep reinforcement learning. We approach this issue from the perspective of self-supervised repr… (see more)esentation learning, leveraging reward-free exploratory data to pretrain encoder networks. We employ a novel combination of latent dynamics modelling and goal-reaching objectives, which exploit the inherent structure of data in reinforcement learning. We demonstrate that our method scales well with network capacity and pretraining data. When evaluated on the Atari 100k data-efficiency benchmark, our approach significantly outperforms previous methods combining unsupervised pretraining with task-specific finetuning, and approaches human-level performance.
2021-01-01
(published)
www.semanticscholar.org
Deep LDA-Pruned Nets for Efficient Facial Gender Classification
Qing Tian
Tal Arbel
James J. Clark
Many real-time tasks, such as human-computer interac-tion, require fast and efficient facial gender classification. Although deep CNN nets… (see more) have been very effective for a mul-titude of classification tasks, their high space and time de-mands make them impractical for personal computers and mobile devices without a powerful GPU. In this paper, we develop a 16-layer, yet lightweight, neural network which boosts efficiency while maintaining high accuracy. Our net is pruned from the VGG-16 model [35] starting from the last convolutional (conv) layer where we find neuron activations are highly uncorrelated given the gender. Through Fisher’s Linear Discriminant Analysis (LDA) [8], we show that this high decorrelation makes it safe to discard directly last conv layer neurons with high within-class variance and low between-class variance. Combined with either Support Vector Machines (SVM) or Bayesian classification, the reduced CNNs are capable of achieving comparable (or even higher) accuracies on the LFW and CelebA datasets than the original net with fully connected layers. On LFW, only four Conv5 3 neurons are able to maintain a comparably high recognition accuracy, which results in a reduction of total network size by a factor of 70X with a 11 fold speedup. Comparisons with a state-of-the-art pruning method [12] (as well as two smaller nets [20, 24]) in terms of accuracy loss and convolutional layers pruning rate are also provided.
2021-01-01
(published)
www.semanticscholar.org
Deep Reinforcement Learning at the Edge of the Statistical Precipice
Rishabh Agarwal
Max Schwarzer
Pablo Samuel Castro
Aaron Courville
Marc Gendron-Bellemare
Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing their relative performance on a large suite of tasks. M… (see more)ost published results on deep RL benchmarks compare point estimates of aggregate performance such as mean and median scores across tasks, ignoring the statistical uncertainty implied by the use of a finite number of training runs. Beginning with the Arcade Learning Environment (ALE), the shift towards computationally-demanding benchmarks has led to the practice of evaluating only a small number of runs per task, exacerbating the statistical uncertainty in point estimates. In this paper, we argue that reliable evaluation in the few run deep RL regime cannot ignore the uncertainty in results without running the risk of slowing down progress in the field. We illustrate this point using a case study on the Atari 100k benchmark, where we find substantial discrepancies between conclusions drawn from point estimates alone versus a more thorough statistical analysis. With the aim of increasing the field's confidence in reported results with a handful of runs, we advocate for reporting interval estimates of aggregate performance and propose performance profiles to account for the variability in results, as well as present more robust and efficient aggregate metrics, such as interquartile mean scores, to achieve small uncertainty in results. Using such statistical tools, we scrutinize performance evaluations of existing algorithms on other widely used RL benchmarks including the ALE, Procgen, and the DeepMind Control Suite, again revealing discrepancies in prior comparisons. Our findings call for a change in how we evaluate performance in deep RL, for which we present a more rigorous evaluation methodology, accompanied with an open-source library rliable, to prevent unreliable results from stagnating the field. This work received an outstanding paper award at NeurIPS 2021.
openreview.net
Embedding Signals on Knowledge Graphs with Unbalanced Diffusion Earth Mover's Distance
Alexander Tong
Guillaume Huguet
Dennis L. Shung
Amine Natik
Manik Kuchroo
Guillaume Lajoie
Guy Wolf
Smita Krishnaswamy
In modern relational machine learning it is common to encounter large graphs that arise via interactions or similarities between observation… (see more)s in many domains. Further
2021-01-01
arXiv.org (preprint)
dblp.uni-trier.de
Embedding Signals on Knowledge Graphs with Unbalanced Diffusion Earth Mover's Distance
Alexander Tong
Guillaume Huguet
Dennis Shung
Amine Natik
Manik Kuchroo
Guillaume Lajoie
Guy Wolf
Smita Krishnaswamy
In modern relational machine learning it is common to encounter large graphs that arise via interactions or similarities between observation… (see more)s in many domains. Further
2021-01-01
arXiv.org (preprint)
dblp.uni-trier.de
Enjeux juridiques propres au modèle émergent des patients accompagnateurs dans les milieux de soins au Québec (Legal Issues Arising from the Emerging Model of Accompanying Patients in the Quebec Healthcare System)
Léa Boutrouille
Catherine Régis
Marie-Pascale Pomey
2021-01-01
SSRN Electronic Journal (published)
doi.org
Estimating the Impact of an Improvement to a Revenue Management System: An Airline Application
Greta Laage
Emma Frejinger
William Hamilton
Andrea Lodi
Guillaume Rabusseau
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
Faults in deep reinforcement learning programs: a taxonomy and a detection approach
Amin Nikanjam
Mohammad Mehdi Morovati
Foutse Khomh
Houssem Ben Braiek
2021-01-01
ArXiv (preprint)
doi.org
arxiv.org
Guest Editorial Explainable AI: Towards Fairness, Accountability, Transparency and Trust in Healthcare
Arash Shaban-Nejad
Martin Michalowski
John S. Brownstein
David Buckeridge
2021-01-01
IEEE journal of biomedical and health informatics (published)
doi.org
Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
Joelle Pineau
Philippe Vincent‐lamarre
Koustuv Sinha
Vincent Larivière
Alina Beygelzimer
Florence D'alche-buc
E. Fox
Hugo Larochelle
arxiv.org
Inspecting the Factuality of Hallucinated Entities in Abstractive Summarization
Meng Cao
Yue Dong
Jackie Cheung
State-of-the-art abstractive summarization systems often generate hallucinations ; i.e., content that is not directly inferable from the sou… (see more)rce text. Despite being assumed incorrect, many of the hallucinated contents are consistent with world knowledge (factual hallucinations). Including these factual hallucinations into a summary can be beneficial in providing additional background information. In this work, we propose a novel detection approach that separates factual from non-factual hallucinations of entities. Our method is based on an entity’s prior and posterior probabilities according to pre-trained and finetuned masked language models, respectively. Empirical re-sults suggest that our method vastly outperforms three strong baselines in both accuracy and F1 scores and has a strong correlation with human judgements on factuality classification tasks. Furthermore, our approach can provide insight into whether a particular hallucination is caused by the summarizer’s pre-training or fine-tuning step. 1
2021-01-01
arXiv.org (preprint)
dblp.uni-trier.de
Inspecting the Factuality of Hallucinated Entities in Abstractive Summarization
Meng Cao
Yue Dong
Jackie Cheung
State-of-the-art abstractive summarization systems often generate hallucinations ; i.e., content that is not directly inferable from the sou… (see more)rce text. Despite being assumed incorrect, many of the hallucinated contents are consistent with world knowledge (factual hallucinations). Including these factual hallucinations into a summary can be beneficial in providing additional background information. In this work, we propose a novel detection approach that separates factual from non-factual hallucinations of entities. Our method is based on an entity’s prior and posterior probabilities according to pre-trained and finetuned masked language models, respectively. Empirical re-sults suggest that our method vastly outperforms three strong baselines in both accuracy and F1 scores and has a strong correlation with human judgements on factuality classification tasks. Furthermore, our approach can provide insight into whether a particular hallucination is caused by the summarizer’s pre-training or fine-tuning step. 1
2021-01-01
arXiv.org (preprint)
dblp.uni-trier.de