Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds



Shinji Ito , Taira Tsuchiya , Junya Honda

* Accepted for presentation at the 35th Annual Conference on Learning Theory (COLT 2022). Only the extended abstract will appear in the conference proceedings 

   Access Paper or Ask Questions

Globally Optimal Algorithms for Fixed-Budget Best Arm Identification



Junpei Komiyama , Taira Tsuchiya , Junya Honda

* fixed title typo 

   Access Paper or Ask Questions

Globally Optimal Algorithms for Fixed-Budged Best Arm Identification



Junpei Komiyama , Taira Tsuchiya , Junya Honda


   Access Paper or Ask Questions

The Survival Bandit Problem



Charles Riou , Junya Honda , Masashi Sugiyama


   Access Paper or Ask Questions

Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs



Shinji Ito , Taira Tsuchiya , Junya Honda


   Access Paper or Ask Questions

Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits



Junpei Komiyama , Edouard Fouché , Junya Honda


   Access Paper or Ask Questions

Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences



Ikko Yamane , Junya Honda , Florian Yger , Masashi Sugiyama

* ICML 2021 version with correction to Figure 1 

   Access Paper or Ask Questions

Combinatorial Pure Exploration with Full-bandit Feedback and Beyond: Solving Combinatorial Optimization under Uncertainty with Limited Observation



Yuko Kuroki , Junya Honda , Masashi Sugiyama

* Preprint of an Invited Review Article 

   Access Paper or Ask Questions

Online Dense Subgraph Discovery via Blurred-Graph Feedback



Yuko Kuroki , Atsushi Miyauchi , Junya Honda , Masashi Sugiyama

* ICML2020 

   Access Paper or Ask Questions

Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring



Taira Tsuchiya , Junya Honda , Masashi Sugiyama

* 40 pages, 4 figures 

   Access Paper or Ask Questions

1
2
3
>>