Publications

Statistical Complexity of Soft Bellman Residual Minimization

Enoch Hyunwook Kang^*, Kyoungseok Jang^*
* Equal contribution

Conference on Neural Information Processing Systems · Main Track · Accepted as Poster

Sparse Linear Bandits with Fixed Sparsity Support: Adversarial and Stochastic Regimes

Kyoungseok Jang, Nam Tran, Nicolò Cesa-Bianchi

The Conference on Artificial Intelligence and Statistics

GL-LowPopArt: A Nearly Instance-Wise Minimax Estimator for (Adaptive) Generalized Linear Low-Rank Trace Regression

Junghyun Lee, Kyoungseok Jang, Kwang-Sung Jun, Milan Vojnovic, Se-Young Yun

The Conference on Artificial Intelligence and Statistics

Rate-optimal Design for Anytime Best Arm Identification

Junpei Komiyama, Kyoungseok Jang, Honda Junya

The Conference on Artificial Intelligence and Statistics

Online Linear Regression with Paid Stochastic Features

Nadav Merlis, Kyoungseok Jang, Nicolò Cesa-Bianchi

The Association for the Advancement of Artificial Intelligence

Fixed Confidence Best Arm Identification in the Bayesian Setting

Kyoungseok Jang, Junpei Komiyama, Kazutoshi Yamazaki

Conference on Neural Information Processing Systems

Sparsity-Agnostic Linear Bandits with Adaptive Adversaries

Tianyuan Jin, Kyoungseok Jang, Nicolò Cesa-Bianchi

Conference on Neural Information Processing Systems

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

Kyoungseok Jang, Kwang-Sung Jun, Chicheng Zhang

International Conference on Machine Learning

Better-than-KL PAC-Bayes Bounds

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

Conference on Learning Theory

Tighter PAC-Bayes Bound through Coin-Betting

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

Conference on Learning Theory

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

Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun

Conference on Neural Information Processing Systems

Improved Regret Bounds of Bilinear Bandits using Action Space Analysis

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

International Conference on Machine Learning

Globally Convergent Offline Reinforcement Learning with Bellman Residual Minimization

Byungjun Park, Minhyeok Park, Enoch H. Kang, Kyoungseok Jang

Efficient Algorithms for Contextual Apple Tasting with Log-Loss

Byeongwoo An, Kapilan Balagopalan, Sehwa Jeong, Jiun Jeong, Kyoungseok Jang, Hyowon Wi, Noseong Park, Gi-Soo Kim, Kwang-Sung Jun