Publications


Machine Learning Researcher

Official Publications


Fixed Confidence Best Arm Identification in the Bayesian Setting

Kyoungseok Jang, Junpei Komiyama, Kazutoshi Yamazaki

In Conference on Neural Information Processing Systems (NeurIPS), accepted, 2024 link

 

Sparsity-Agnostic Linear Bandits with Adaptive Adversaries

Tianyuan Jin, Kyoungseok Jang, Nicolò Cesa-Bianchi

In Conference on Neural Information Processing Systems (NeurIPS), accepted, 2024 link

 

Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits

Kyoungseok Jang, Kwang-sung Jun, Chicheng Zhang

In International Conference on Machine Learning (ICML), accepted, 2024 link

 

Better-than-KL PAC-Bayes bounds

Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona

In Conference on Learning Theory (COLT), accepted, 2024 link

 

Tighter PAC-Bayes bound through Coin-Betting

Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona

In Conference on Learning Theory (COLT), accepted, 2023 link

 

PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits

Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun

In Conference on Neural Information Processing Systems (NeurIPS), accepted, 2022 link

 

Improved Regret Bounds of Bilinear Bandits using Action Space Analysis.

Kyoungseok Jang, Kwang-Sung Jun, Se Young Yun, Wanmo Kang.

In International Conference on Machine Learning (ICML), accepted, 2021 link

 

 

Preprints


 

 

Workshop paper


Fixed Confidence Best Arm Identification in the Bayesian Setting

Kyoungseok Jang, Junpei Komiyama, Kazutoshi Yamazaki

In the second RL theory workshop (co-located with COLT 2024), poster presentation, 2024

 

Improved Time-Uniform PAC-Bayes Bounds using Coin Betting

Kyoungseok Jang, Kwang-sung Jun, Ilja Kuzborskij, Francesco Orabona

In International Conference on Machine Learning (ICML) Workshop “PAC-Bayes meets Interactive Learning”, Contributed talk, 2023