| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Bootstrap Your Own Latent: A new approach to self-supervised learning
Abstract : We investigate and provide new insights on the sampling rule called Top-Two Thompson Sampling (TTTS). In particular, we justify its use for fixed-confidence best-arm identification. We further propose a variant of TTTS called Top-Two Transportation Cost (T3C), which disposes of the computational burden of TTTS. As our main contribution, we provide the first sample complexity analysis of TTTS and T3C when coupled with a very natural Bayesian stopping rule, for bandits with Gaussian rewards, solving one of the open questions raised by Russo (2016). We also provide new posterior convergence results for TTTS under two models that are commonly used in practice: bandits with Gaussian and Bernoulli rewards and conjugate priors.
https://hal.inria.fr/hal-02869787
Contributor : Michal Valko <>
Submitted on : Thursday, February 25, 2021 - 4:52:13 PM
Last modification on : Friday, February 26, 2021 - 10:36:31 AM
Contributor : Michal Valko <>
Submitted on : Thursday, February 25, 2021 - 4:52:13 PM
Last modification on : Friday, February 26, 2021 - 10:36:31 AM
File
grill2020bootstrap.pdf
Files produced by the author(s)