PAC-Bayesian Analysis of Contextual Bandits

By Yevgeny Seldin, Peter Auer, François Laviolette, John Shawe-Taylor, Ronald Ortner. 2011

48 citations recorded by the source corpus.

Subfields: Reinforcement Learning, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

In Statistical Learning Theory

Citations in the corpus

PAC-Bayesian Theory Meets Bayesian Inference (2016, neutral): “However, despite the amount of work dedicated to this statistical learning theory—many authors improved the initial results [9, 29, 33, 43, 48] and/or generalized them for various machine learning setups [4, 14, 20, 28, 38, 44, 45, 46]—it is mostly used as a frequentist method.”
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (2012, neutral): “[150] using new sophisticated tools of PAC-Bayesian analysis.”
Convex Optimization: Algorithms and Complexity (2015, unknown): “However, recent theoretical results on PAC-Bayesian analysis of the bandit case may provide useful tools for further development of this area [Seldin et al., 2011a,b].”
User-friendly introduction to PAC-Bayes bounds (2021, background): “Some authors derived strategies or regret bounds directly from PAC-Bayes bounds [174, 175].”
Online Clustering of Bandits (2014, methodology): “…(e.g., (Auer, 2002; Langford & Zhang, 2007; Li et al., 2010; Chu et al., 2011; Bogers, 2010; AbbasiYadkori et al., 2011; Crammer & Gentile, 2011; Krause & Ong, 2011), and references therein) have rapidly become a * reference algorithmic technique for implementing adaptive recommender systems.”
A Neural Networks Committee for the Contextual Bandit Problem (2014, background): “Seldin et al [14] modelize the contexts by state sets, which are associated with bandit problems.”
G-Learning: Taming the Noise in Reinforcement Learning via Soft Updates (2015, background): “One hint to what a good schedule of β can be is provided by the PAC-Bayes bound, developed generally in [20, 21, 22], and for reinforcement learning in [23, 24, 10].”
PAC-Bayes-Bernstein Inequality for Martingales and its Application to Multiarmed Bandits (2011, methodology): “See also our follow-up work on PAC-Bayesian inequalities for martingales (Seldin et al., 2011b) c© 2012 Y. Seldin, N. Cesa-Bianchi, P. Auer, F. Laviolette & J. Shawe-Taylor. ar X iv :1 11 0.”
Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm (2015, methodology): “stering (Seldin and Tishby, 2009, 2010), Martingales (Seldin et al., 2012), UStatistics of higher order (Lever et al., 2013) or other non-i.i.d. settings (Ralaivola et al., 2010), Multi-armed Bandit (Seldin et al., 2011) and Reinforcement Learning (Fard and Pineau, 2010; Fard et al., 2011). Acknowle”
Bayesian Counterfactual Risk Minimization (2018, methodology): “[28] to analyze contextual bandits in the PAC-Bayes framework.”