Bootstrap Your Own Latent: A new approach to self-supervised learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Bootstrap Your Own Latent: A new approach to self-supervised learning

Jean-Bastien Grill
  • Function : Author
  • PersonId : 972490
Florian Strub
Florent Altché
  • Function : Author
  • PersonId : 1027053
Corentin Tallec
  • Function : Author
  • PersonId : 1092021
Pierre H Richemond
  • Function : Author
  • PersonId : 1073235
Carl Doersch
  • Function : Author
Bilal Piot
  • Function : Author
Rémi Munos
  • Function : Author
  • PersonId : 836863
Michal Valko

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.
Fichier principal
Vignette du fichier
grill2020bootstrap.pdf (4.38 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02869787 , version 1 (16-06-2020)
hal-02869787 , version 2 (25-02-2021)

Identifiers

Cite

Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H Richemond, et al.. Bootstrap Your Own Latent: A new approach to self-supervised learning. Neural Information Processing Systems, 2020, Montréal, Canada. ⟨hal-02869787v2⟩
573 View
798 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More