Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling

Abstract : Stochastic Rank-One Bandits (Katarya et al, (2017a,b)) are a simple framework for regret minimization problems over rank-one matrices of arms. The initially proposed algorithms are proved to have logarithmic regret, but do not match the existing lower bound for this problem. We close this gap by first proving that rank-one bandits are a particular instance of unimodal bandits, and then providing a new analysis of Unimodal Thompson Sampling (UTS), initially proposed by Paladino et al (2017). We prove an asymptotically optimal regret bound on the frequentist regret of UTS and we support our claims with simulations showing the significant improvement of our method compared to the state-of-the-art.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02396943
Contributor : Emilie Kaufmann <>
Submitted on : Friday, December 6, 2019 - 11:50:44 AM
Last modification on : Wednesday, January 8, 2020 - 1:33:11 AM

Files

Identifiers

  • HAL Id : hal-02396943, version 1
  • ARXIV : 1912.03074

Citation

Cindy Trinh, Emilie Kaufmann, Claire Vernade, Richard Combes. Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling. 2019. ⟨hal-02396943⟩

Share

Metrics

Record views

38

Files downloads

51