Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
IBISML |
2022-12-22 15:55 |
Kyoto |
Kyoto University (Primary: On-site, Secondary: Online) |
IBISML2022-48 |
[more] |
IBISML2022-48 pp.30-37 |
NC, IBISML, IPSJ-BIO, IPSJ-MPS [detail] |
2022-06-28 14:20 |
Okinawa |
(Primary: On-site, Secondary: Online) |
On DC Relaxation of Information-directed Sampling in Combinatorial Multi-armed Bandit Problem Junta Fujinaga (Kyoto Univ.), Taira Tsuchiya, Junya Honda (Kyoto Univ./RIKEN) NC2022-18 IBISML2022-18 |
[more] |
NC2022-18 IBISML2022-18 pp.129-136 |
IT, EMM |
2018-05-18 13:20 |
Tokyo |
Ookayama Campus, Tokyo Institute of Technology |
[Invited Talk]
Recent Advances on Capacity-achieving Coding Schemes for Asymmetric Channels Junya Honda (Univ. Tokyo) IT2018-9 EMM2018-9 |
[more] |
IT2018-9 EMM2018-9 pp.45-51 |
IBISML |
2017-11-10 13:00 |
Tokyo |
Univ. of Tokyo |
Good Arm Identification via Bandit Feedback Hideaki Kano, Junya Honda (UTokyo/RIKEN), Kentaro Sakamaki (UTokyo), Kentaro Matsuura (Johnson & Johnson), Atsuyoshi Nakamura (HU), Masashi Sugiyama (RIKEN/UTokyo) IBISML2017-82 |
In this paper, we consider and discuss a new stochastic multi-armed bandit problem called {em good arm identification} (... [more] |
IBISML2017-82 pp.339-346 |
IBISML |
2016-11-17 14:00 |
Kyoto |
Kyoto Univ. |
[Poster Presentation]
Estimating Proton Conductivity in Crystals by using Guassian Process and Dynamic Programming Kenta Kanamori (NITech), Kazuaki Toyoura (Kyoto Univ.), Shinichi Nakajima (TU Berlin), Atsuto Seko (Kyoto Univ.), Masayuki Karasuyama (NITech), Akihide Kuwabara (JFCC), Junya Honda (Tokyo Univ.), Kazuki Shitara (JFCC), Motoki Shiga (Gifu Univ.), Ichiro Takeuchi (NITech) IBISML2016-73 |
In material science, $proton conductivity$ is very important property for designing new battery and it is defined as max... [more] |
IBISML2016-73 pp.191-198 |
NC, IPSJ-BIO, IBISML, IPSJ-MPS (Joint) [detail] |
2015-06-23 16:10 |
Okinawa |
Okinawa Institute of Science and Technology |
Optimal Algorithms in Dueling Bandit Problem Junpei Komiyama, Junya Honda (U-Tokyo), Hisashi Kashima (Kyoto University), Hiroshi Nakagawa (U-Tokyo) IBISML2015-14 |
We study the K-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is... [more] |
IBISML2015-14 pp.87-94 |
IT |
2015-01-30 16:10 |
Chiba |
|
On Asymptotic Expansion of Random Coding Error Probability under Lattice Condition Junya Honda (Univ. of Tokyo) IT2014-61 |
We consider exact asymptotics of random coding error probability of memoryless channels. We can derive an evaluation of ... [more] |
IT2014-61 pp.41-46 |
IT |
2014-07-17 09:45 |
Hyogo |
Kobe University |
Construction of Almost Instantaneous FV codes based on Integer Programming Masato Tsuchihasi, Hirosuke Yamamoto, Junya Honda (Univ. of Tokyo) IT2014-11 |
The Almost Instantaneous FV (AIFV) code, which consists of
several code trees with incomplete internal nodes, can atta... [more] |
IT2014-11 pp.1-6 |
IT |
2012-07-20 15:50 |
Aichi |
Toyota Technological Institute |
Variable Length Coding of Asymmetric Channels using a Homophonic Code Junya Honda, Hirosuke Yamamoto (Univ. of Tokyo) IT2012-27 |
[more] |
IT2012-27 pp.109-114 |
IBISML |
2012-06-20 11:00 |
Kyoto |
Campus plaza Kyoto |
On a Non-asymptotic Analysis Using Large Deviation Principles in the Multiarmed Bandit Problem Junya Honda, Akimichi Takemura (Univ. of Tokyo) IBISML2012-10 |
In reinforcement learning a tradeoff between exploration and exploitation is considered.
Multiarmed bandit problems for... [more] |
IBISML2012-10 pp.65-72 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2011-09-05 11:00 |
Hokkaido |
|
Multiarmed Bandit Algorithms Based on Empirical Moments Junya Honda, Akimichi Takemura (Univ. of Tokyo) PRMU2011-60 IBISML2011-19 |
[more] |
PRMU2011-60 IBISML2011-19 pp.15-22 |
IT |
2008-07-24 15:15 |
Chiba |
University of Tokyo, Kashiwa Campus |
Source Coding with LDPC code using Linear Programming Junya Honda (Univ. of Tokyo), Shigeki Miyake (NTT), Hirosuke Yamamoto (Univ. of Tokyo), Mitsuru Maruyama (NTT) IT2008-13 |
In channel coding, Feldman showed that linear programming can be used instead of the sum-product algorithm in the decodi... [more] |
IT2008-13 pp.27-32 |