Fetching the paper…

Reading the bibliography…

2017

Ensemble Sampling

Lu, Xiuyuan, Van Roy, Benjamin

Original
PDF
Post on X

Understand

Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems.

In its basic form, the algorithm requires computing and sampling from a posterior distribution over models, which is tractable only for simple special cases.
This paper develops ensemble sampling, which aims to approximate Thompson sampling while maintaining tractability even in the face of complex models such as neural networks.
Ensemble sampling dramatically expands on the range of applications for which Thompson sampling is viable.

Ensemble Sampling · Around

Built on

On the likelihood that one unknown probability exceeds another in view of the evidence of two samples
Original
W.R. Thompson · 1933
Earlier work this paper cites.
Ensemble learning
Thomas G Dietterich · 2002
Earlier work this paper cites.
Gaussian sampling by local perturbations
George Papandreou and Alan L Yuille · 2010
Earlier work this paper cites.

Similar

An empirical evaluation of Thompson sampling
Olivier Chapelle and Lihong Li · 2011
Cited alongside, same era.
Weight uncertainty in neural networks
Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, and Daan Wierstra · 2015
Cited alongside, same era.
Dropout as a Bayesian approximation: Representing model uncertainty in deep learning
Yarin Gal and Zoubin Ghahramani · 2016
Cited alongside, same era.

Then

Online algorithms for parameter mean and variance estimation in dynamic regression
Original
Carlos Gómez-Uribe · 2016
Later among the works it cites.
Deep exploration via bootstrapped DQN
Ian Osband, Charles Blundell, Alexander Pritzel, and Benjamin Van Roy · 2016
Later among the works it cites.
An analysis of ensemble sampling
Chao Qin, Zheng Wen, Xiuyuan Lu, and Benjamin Van Roy · 2022
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…