Publications

Accelerating Smooth Games by Manipulating Spectral Shapes
Waiss Azizian
Damien Scieur
Ioannis Mitliagkas
Simon Lacoste-Julien
Gauthier Gidel
2020-06-03
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
arxiv.org
Deep Active Learning: Unified and Principled Method for Query and Training
Changjian Shui
Fan Zhou
Christian Gagné
Boyu Wang
2020-06-03
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
arxiv.org
Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
Tianyu Li
Bogdan Mazoure
Doina Precup
Guillaume Rabusseau
2020-06-03
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
arxiv.org
Old Dog Learns New Tricks: Randomized UCB for Bandit Problems
Sharan Vaswani
Abbas Mehrabian
Audrey Durand
Branislav Kveton
2020-06-03
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
arxiv.org
A principled approach for generating adversarial images under non-smooth dissimilarity metrics
Aram-Alexandre Pooladian
Chris Finlay
Tim Hoheisel
Adam M. Oberman
2020-06-03
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
arxiv.org
A Reduction from Reinforcement Learning to No-Regret Online Learning
Ching-An Cheng
Remi Tachet des Combes
Byron Boots
Geoff Gordon
We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "… (see more)any" online algorithm with sublinear regret can generate policies with provable performance guarantees. This new perspective decouples the RL problem into two parts: regret minimization and function approximation. The first part admits a standard online-learning analysis, and the second part can be quantified independently of the learning algorithm. Therefore, the proposed reduction can be used as a tool to systematically design new RL algorithms. We demonstrate this idea by devising a simple RL algorithm based on mirror descent and the generative-model oracle. For any
2020-06-03
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
arxiv.org
Stochastic Neural Network with Kronecker Flow
Chin-Wei Huang
Ahmed Touati
Pascal Vincent
Gintare Karolina Dziugaite
Alexandre Lacoste
Aaron Courville
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.
2020-06-03
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
arxiv.org
Value Preserving State-Action Abstractions
David Abel
Nathan Umbanhowar
Khimya Khetarpal
Dilip Arumugam
Doina Precup
Michael L. Littman
Abstraction can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information… (see more), potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.ion can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information, potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.
2020-06-03
International Conference on Artificial Intelligence and Statistics (published)
dblp.uni-trier.de
Value Preserving State-Action Abstractions
David Abel
Nathan Umbanhowar
Khimya Khetarpal
Dilip Arumugam
Doina Precup
Michael L. Littman
Abstraction can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information… (see more), potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.ion can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information, potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.
2020-06-03
International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
Restless bandits: indexability and computation of Whittle index
Nima Akbarzadeh
Aditya Mahajan
Restless bandits are a class of sequential resource allocation problems concerned with allocating one or more resources among several altern… (see more)ative processes where the evolution of the process depends on the resource allocated to them. Such models capture the fundamental trade-offs between exploration and exploitation. In 1988, Whittle developed an index heuristic for restless bandit problems which has emerged as a popular solution approach due to its simplicity and strong empirical performance. The Whittle index heuristic is applicable if the model satisfies a technical condition known as indexability. In this paper, we present two general sufficient conditions for indexability and identify simpler to verify refinements of these conditions. We then present a general algorithm to compute Whittle index for indexable restless bandits. Finally, we present a detailed numerical study which affirms the strong performance of the Whittle index heuristic.
2020-06-01
arXiv.org (preprint)
dblp.uni-trier.de
GIANT: Scalable Creation of a Web-scale Ontology
Bang Liu
Weidong Guo
Di Niu
Jinwen Luo
Chaoyue Wang
Zhen Wen
Yu Xu
2020-05-31
Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data (published)
doi.org
arxiv.org
Current works and future directions on application of machine learning in primary care
Samira Abbasgholizadeh-Rahimi
Vera Granikov
Pierre Pluye
In this short paper, we explained current machine learning works in primary care based on a scoping review that we performed. The performed … (see more)review was in line with the methodological framework proposed by Colquhoun and colleagues. Lastly, we discussed our observations and gave important directions to the future studies in this fast-growing area.
2020-05-27
International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems (published)
doi.org