Gilles Stoltz
Artificial Intelligence · 2005–2012
A researcher in the Science corpus: 8 papers; trusts 15 researchers and is trusted by 77 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 40 citations into it; #3,630 of 35,345 by trust here, #5,924 by citations
- Management Science and Operations Research — 31 citations into it; #441 of 11,946 by trust here, #473 by citations
- Reinforcement Learning — 20 citations into it; #542 of 2,242 by trust here, #978 by citations
- Statistics and Probability — 17 citations into it
- Statistical Learning Theory — 12 citations into it; #864 of 1,038 by trust here, #730 by citations
- Economics and Econometrics — 8 citations into it
- Game & Decision Theory — 8 citations into it
- Computer Networks and Communications — 7 citations into it
Whom Gilles Stoltz trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Nicolò Cesa-Bianchi
- Peter Auer
- Levente Kocsis
- Robert D. Kleinberg
- Gábor Lugosi
- Mark Herbster
- Rajeev Agrawal
- Csaba Szepesvari
- Elad Hazan
- Manfred K. Warmuth
Who trusts Gilles Stoltz overall
- Sébastien Bubeck
- Daniel Russo
- Nicolò Cesa-Bianchi
- R´emi Munos
- Masrour Zoghi
- Adam D. Bull
- Eric C. Hall
- Ziyun Wang
- Nando de Freitas
- Emilie Kaufmann
Papers from Gilles Stoltz's perspective
Ordered by how strongly the researchers Gilles Stoltz trusts endorse each paper. Same corpus, a different order for every researcher.
- Some aspects of the sequential design of experiments
- Prediction, learning, and games
- Probability Inequalities for Sums of Bounded Random Variables
- Finite-time Analysis of the Multiarmed Bandit Problem
- Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
- Nearly Tight Bounds for the Continuum-Armed Bandit Problem
- Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis
- ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES
- Efficient projections onto the l1-ball for learning in high dimensions
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
Their papers
- Pure Exploration in Multi-armed Bandits Problems (2009) — 579 citations
- Improved second-order bounds for prediction with expert advice (2005) — 288 citations
- Online Multi-task Learning with Hard Constraints (2009) — 52 citations
- Kullback–Leibler upper confidence bounds for optimal sequential allocation (2012) — 425 citations
- X-Armed Bandits (2010) — 439 citations
- Mirror Descent Meets Fixed Share (and feels no regret) (2012) — 106 citations
- Pure exploration in finitely-armed and continuous-armed bandits (2011) — 284 citations
- A new look at shifting regret (2012) — 32 citations