Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Zenati, Houssam"'
We address the problem of stochastic combinatorial semi-bandits, where a player selects among $P$ actions from the power set of a set containing $d$ base items. Adaptivity to the problem's structure is essential in order to obtain optimal regret uppe
Externí odkaz:
http://arxiv.org/abs/2402.15171
Counterfactual Risk Minimization (CRM) is a framework for dealing with the logged bandit feedback problem, where the goal is to improve a logging policy using offline data. In this paper, we explore the case where it is possible to deploy learned pol
Externí odkaz:
http://arxiv.org/abs/2302.12120
In many online decision processes, the optimizing agent is called to choose between large numbers of alternatives with many inherent similarities; in turn, these similarities imply closely correlated losses that may confound standard discrete choice
Externí odkaz:
http://arxiv.org/abs/2206.09348
Autor:
Zenati, Houssam, Bietti, Alberto, Diemert, Eustache, Mairal, Julien, Martin, Matthieu, Gaillard, Pierre
In this paper, we tackle the computational efficiency of kernelized UCB algorithms in contextual bandits. While standard methods require a O(CT^3) complexity where T is the horizon and the constant C is related to optimizing the UCB rule, we propose
Externí odkaz:
http://arxiv.org/abs/2202.05638
Autor:
Zenati, Houssam, Bietti, Alberto, Martin, Matthieu, Diemert, Eustache, Gaillard, Pierre, Mairal, Julien
Counterfactual reasoning from logged data has become increasingly important for many applications such as web advertising or healthcare. In this paper, we address the problem of learning stochastic policies with continuous actions from the viewpoint
Externí odkaz:
http://arxiv.org/abs/2004.11722
Autor:
Lecouat, Bruno, Chang, Ken, Foo, Chuan-Sheng, Unnikrishnan, Balagopal, Brown, James M., Zenati, Houssam, Beers, Andrew, Chandrasekhar, Vijay, Kalpathy-Cramer, Jayashree, Krishnaswamy, Pavitra
Supervised deep learning algorithms have enabled significant performance gains in medical image classification tasks. But these methods rely on large labeled datasets that require resource-intensive expert annotation. Semi-supervised generative adver
Externí odkaz:
http://arxiv.org/abs/1812.07832
Autor:
Zenati, Houssam, Romain, Manon, Foo, Chuan Sheng, Lecouat, Bruno, Chandrasekhar, Vijay Ramaseshan
Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge. As Generative Adversarial Networks (GANs) are able to model the comp
Externí odkaz:
http://arxiv.org/abs/1812.02288
Generative Adversarial Networks are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization by approximating a variant of the Laplacian norm using a Monte Carlo ap
Externí odkaz:
http://arxiv.org/abs/1807.04307
Autor:
Mertikopoulos, Panayotis, Lecouat, Bruno, Zenati, Houssam, Foo, Chuan-Sheng, Chandrasekhar, Vijay, Piliouras, Georgios
Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond. By necessity, most theoretical guarantees revolve around convex-concave (or eve
Externí odkaz:
http://arxiv.org/abs/1807.02629
Publikováno v:
Workshop track - ICLR 2018
GANS are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization by approximating the Laplacian norm using a Monte Carlo approximation that is easily computed with
Externí odkaz:
http://arxiv.org/abs/1805.08957