T
Tanguy Urvoy
Researcher at Orange S.A.
Publications - 37
Citations - 577
Tanguy Urvoy is an academic researcher from Orange S.A.. The author has contributed to research in topics: Reinforcement learning & Random forest. The author has an hindex of 12, co-authored 35 publications receiving 513 citations.
Papers
More filters
Journal ArticleDOI
Tracking Web spam with HTML style similarities
TL;DR: This work study and compare several HTML style similarity measures based on both textual and extra-textual features in HTML source code and proposes a flexible algorithm to cluster a large collection of documents according to these measures.
Proceedings Article
Generic Exploration and K-armed Voting Bandits
TL;DR: A generic pure-exploration algorithm, able to cope with various utility functions from multi-armed bandits settings to dueling bandits, is proposed, to offer a natural generalization of Dueling bandits for situations where the environment parameters reflect the idiosyncratic preferences of a mixed crowd.
Book ChapterDOI
Contextual Bandit for Active Learning: Active Thompson Sampling
TL;DR: A sequential algorithm named Active Thompson Sampling (ATS) is proposed, which, in each round, assigns a sampling distribution on the pool, samples one point from this distribution, and queries the oracle for this sample point label.
Proceedings Article
Tracking Web Spam with Hidden Style Similarity
TL;DR: This paper presents a (hidden) style similarity based on extra-textual features in html source code and describes a method to clusterize a large collection of documents according to this measure.
Proceedings Article
Random Forest for the Contextual Bandit Problem
TL;DR: An online random forest algorithm is proposed to address the contextual bandit problem, based on the sample complexity needed to find the optimal decision stump, and it is shown that the proposed algorithm is optimal up to logarithmic factors.