S
Zodix
Study
Academic Library
Search
Shelves
Open access
Sign in
Search or jump to…
⌘K
Junya Honda · Study
Home
/
Author
Junya Honda
8 works
· latest 2018
· 1 institutions
cluster: provisional
Follow
Claim this profile
h-index
8
i10
8
Citations
603
Works here
8
10
11
13
15
17
18
Most cited in this library
An Asymptotically Optimal Bandit Algorithm for Bounded Support Models.
2010 · 139 citations
Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays
2015 · 104 citations
An asymptotically optimal policy for finite support models in the multiarmed bandit problem
2011 · 94 citations
Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards
2015 · 67 citations
Normal bandits of unknown means and variances
2017 · 63 citations
Works
8 shown
Nonconvex Optimization for Regression with Fairness Constraints.
International Conference on Machine Learning
·
2018
·
4 authors
·
other
60
citations
A fully adaptive algorithm for pure exploration in linear bandits.
International Conference on Artificial Intelligence and Statistics
·
2018
·
3 authors
·
other
33
citations
Normal bandits of unknown means and variances
Journal of Machine Learning Research
·
2017
·
3 authors
63
citations
Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays
arXiv (Cornell University)
·
2015
·
3 authors
·
preprint
·
Open access
104
citations
Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards
Journal of Machine Learning Research
·
2015
·
2 authors
67
citations
Optimality of Thompson Sampling for Gaussian Bandits Depends on Priors
arXiv (Cornell University)
·
2013
·
2 authors
·
preprint
·
Open access
43
citations
An asymptotically optimal policy for finite support models in the multiarmed bandit problem
Machine Learning
·
2011
·
2 authors
·
Open access
94
citations
An Asymptotically Optimal Bandit Algorithm for Bounded Support Models.
·
2010
·
2 authors
139
citations