Kwang-Sung Jun

85 papers A* 22A 8B 2Journal 46Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Coverage Improvement and Fast Convergence of On-policy Preference Learning. CoRR Juno Kim, Jihun Yun, Jason D. Lee, Kwang-Sung Jun
2026	J	`jnl`	Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors. CoRR Kapilan Balagopalan, Yinan Li, Yao Zhao, Tuan Ngo Nguyen, Anton Daitche, Houssam Nassif, Kwang-Sung Jun
2026	J	`jnl`	Nearly Optimal Active Preference Learning and Its Application to LLM Alignment. CoRR Yao Zhao, Kwang-Sung Jun
2026	J	`jnl`	Regularized Online RLHF with Generalized Bilinear Preferences. CoRR Junghyun Lee, Minju Hong, Kwang-Sung Jun, Chulhee Yun, Se-Young Yun
2025	J	`jnl`	Achieving adaptivity and optimality for multi-armed bandits using Exponential-Kullback Leiblier Maillard Sampling. CoRR Hao Qin, Kwang-Sung Jun, Chicheng Zhang
2025	J	`jnl`	Alignment as Distribution Learning: Your Preference Model is Explicitly a Language Model. CoRR Jihun Yun, Juno Kim, Jongho Park, Junhyuck Kim, Jongha Jon Ryu, Jaewoong Cho, Kwang-Sung Jun
2025	A*	`conf`	Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification. ICML Kapilan Balagopalan, Tuan Ngo Nguyen, Yao Zhao, Kwang-Sung Jun
2025	J	`jnl`	GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression. CoRR Junghyun Lee, Kyoungseok Jang, Kwang-Sung Jun, Milan Vojnovic, Se-Young Yun
2025	A	`conf`	HAVER: Instance-Dependent Error Bounds for Maximum Mean Estimation and Applications to Q-Learning and Monte Carlo Tree Search. AISTATS Tuan Nguyen, Jay Barrett, Kwang-Sung Jun
2025	A*	`conf`	Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing. COLT Jongha Jon Ryu, Jeongyeol Kwon, Benjamin Koppe, Kwang-Sung Jun
2025	J	`jnl`	Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing. CoRR Jongha Jon Ryu, Jeongyeol Kwon, Benjamin Koppe, Kwang-Sung Jun
2025	J	`jnl`	Learning Explainable Dense Reward Shapes via Bayesian Optimization. CoRR Ryan Koo, Ian Yang, Vipul Raheja, Mingyi Hong, Kwang-Sung Jun, Dongyeop Kang
2025	A	`conf`	Minimum Empirical Divergence for Sub-Gaussian Linear Bandits. AISTATS Kapilan Balagopalan, Kwang-Sung Jun
2025	J	`jnl`	Second-Order Bounds for [0,1]-Valued Regression via Betting Loss. CoRR Yinan Li, Kwang-Sung Jun
2024	A*	`conf`	A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits. NeurIPS Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
2024	J	`jnl`	A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits. CoRR Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
2024	A*	`conf`	Adaptive Experimentation When You Can't Experiment. NeurIPS Yao Zhao, Kwang-Sung Jun, Tanner Fiez, Lalit Jain
2024	J	`jnl`	Adaptive Experimentation When You Can't Experiment. CoRR Yao Zhao, Kwang-Sung Jun, Tanner Fiez, Lalit Jain
2024	A*	`conf`	Better-than-KL PAC-Bayes Bounds. COLT Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona
2024	J	`jnl`	Better-than-KL PAC-Bayes Bounds. CoRR Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona
2024	A*	`conf`	Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits. ICML Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun
2024	J	`jnl`	Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits. CoRR Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun
2024	J	`jnl`	Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification. CoRR Kapilan Balagopalan, Tuan Ngo Nguyen, Yao Zhao, Kwang-Sung Jun
2024	J	`jnl`	HAVER: Instance-Dependent Error Bounds for Maximum Mean Estimation and Applications to Q-Learning. CoRR Tuan Ngo Nguyen, Kwang-Sung Jun
2024	A	`conf`	Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion. AISTATS Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
2024	J	`jnl`	Minimum Empirical Divergence for Sub-Gaussian Linear Bandits. CoRR Kapilan Balagopalan, Kwang-Sung Jun
2024	A*	`conf`	Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization. ICML Kwang-Sung Jun, Jungtaek Kim
2024	J	`jnl`	Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization. CoRR Kwang-Sung Jun, Jungtaek Kim
2024	J	`jnl`	Tight Concentrations and Confidence Sequences From the Regret of Universal Portfolio. IEEE Trans. Inf. Theory Francesco Orabona, Kwang-Sung Jun
2024	J	`jnl`	Transfer Learning in Bandits With Latent Continuity. IEEE Trans. Inf. Theory Hyejin Park, Seiyun Shin, Kwang-Sung Jun, Jungseul Ok
2023	J	`jnl`	Graph Sparsifications using Neural Network Assisted Monte Carlo Tree Search. CoRR Alvin Chiu, Mithun Ghosh, Abu Reyan Ahmed, Kwang-Sung Jun, Stephen G. Kobourov, Michael T. Goodrich
2023	J	`jnl`	Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion. CoRR Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
2023	A*	`conf`	Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards. NeurIPS Hao Qin, Kwang-Sung Jun, Chicheng Zhang
2023	J	`jnl`	Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards. CoRR Hao Qin, Kwang-Sung Jun, Chicheng Zhang
2023	J	`jnl`	Nearly Optimal Steiner Trees using Graph Neural Network Assisted Monte Carlo Tree Search. CoRR Abu Reyan Ahmed, Mithun Ghosh, Kwang-Sung Jun, Stephen G. Kobourov
2023	A*	`conf`	Revisiting Simple Regret: Fast Rates for Returning a Good Arm. ICML Yao Zhao, Connor Stephens, Csaba Szepesvári, Kwang-Sung Jun
2023	A*	`conf`	Tighter PAC-Bayes Bounds Through Coin-Betting. COLT Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona
2023	J	`jnl`	Tighter PAC-Bayes Bounds Through Coin-Betting. CoRR Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona
2022	A*	`conf`	An Experimental Design Approach for Regret Minimization in Logistic Bandits. AAAI Blake Mason, Kwang-Sung Jun, Lalit Jain
2022	J	`jnl`	An Experimental Design Approach for Regret Minimization in Logistic Bandits. CoRR Blake Mason, Kwang-Sung Jun, Lalit Jain
2022	A*	`conf`	Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs. NeurIPS Yeoneung Kim, Insoon Yang, Kwang-Sung Jun
2022	A	`conf`	Jointly Efficient and Optimal Algorithms for Logistic Bandits. AISTATS Louis Faury, Marc Abeille, Kwang-Sung Jun, Clément Calauzènes
2022	J	`jnl`	Jointly Efficient and Optimal Algorithms for Logistic Bandits. CoRR Louis Faury, Marc Abeille, Kwang-Sung Jun, Clément Calauzènes
2022	A	`conf`	Maillard Sampling: Boltzmann Exploration Done Optimally. AISTATS Jie Bian, Kwang-Sung Jun
2022	A	`conf`	Norm-Agnostic Linear Bandits. AISTATS Spencer B. Gales, Sunder Sethuraman, Kwang-Sung Jun
2022	J	`jnl`	Norm-Agnostic Linear Bandits. CoRR Spencer Gales, Sunder Sethuraman, Kwang-Sung Jun
2022	A*	`conf`	PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits. NeurIPS Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun
2022	J	`jnl`	PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits. CoRR Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun
2022	J	`jnl`	Revisiting Simple Regret Minimization in Multi-Armed Bandits. CoRR Yao Zhao, Connor Stephens, Csaba Szepesvári, Kwang-Sung Jun
2021	A*	`conf`	Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits. ICML Kwang-Sung Jun, Lalit Jain, Houssam Nassif, Blake Mason
2021	J	`jnl`	Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs. CoRR Yeoneung Kim, Insoon Yang, Kwang-Sung Jun
2021	A*	`conf`	Improved Regret Bounds of Bilinear Bandits using Action Space Analysis. ICML Kyoungseok Jang, Kwang-Sung Jun, Se-Young Yun, Wanmo Kang
2021	J	`jnl`	Maillard Sampling: Boltzmann Exploration Done Optimally. CoRR Jie Bian, Kwang-Sung Jun
2021	J	`jnl`	Tight Concentrations and Confidence Sequences from the Regret of Universal Portfolio. CoRR Francesco Orabona, Kwang-Sung Jun
2021	B	`conf`	Transfer Learning in Bandits with Latent Continuity. ISIT Hyejin Park, Seiyun Shin, Kwang-Sung Jun, Jungseul Ok
2021	J	`jnl`	Transfer Learning in Bandits with Latent Continuity. CoRR Hyejin Park, Seiyun Shin, Kwang-Sung Jun, Jungseul Ok
2020	A*	`conf`	Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality. NeurIPS Kwang-Sung Jun, Chicheng Zhang
2020	J	`jnl`	Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality. CoRR Kwang-Sung Jun, Chicheng Zhang
2020	J	`jnl`	Improved Confidence Bounds for the Linear Logistic Model and Applications to Linear Bandits. CoRR Kwang-Sung Jun, Lalit Jain, Houssam Nassif
2019	A*	`conf`	Bilinear Bandits with Low-rank Structure. ICML Kwang-Sung Jun, Rebecca Willett, Stephen J. Wright, Robert D. Nowak
2019	J	`jnl`	Bilinear Bandits with Low-rank Structure. CoRR Kwang-Sung Jun, Rebecca Willett, Stephen J. Wright, Robert D. Nowak
2019	A*	`conf`	Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. NeurIPS Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona
2019	J	`jnl`	Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration. CoRR Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona
2019	J	`jnl`	Parameter-Free Locally Differentially Private Stochastic Subgradient Descent. CoRR Kwang-Sung Jun, Francesco Orabona
2019	A*	`conf`	Parameter-Free Online Convex Optimization with Sub-Exponential Noise. COLT Kwang-Sung Jun, Francesco Orabona
2019	J	`jnl`	Parameter-free Online Convex Optimization with Sub-Exponential Noise. CoRR Kwang-Sung Jun, Francesco Orabona
2018	A*	`conf`	Adversarial Attacks on Stochastic Bandits. NeurIPS Kwang-Sung Jun, Lihong Li, Yuzhe Ma, Xiaojin (Jerry) Zhu
2018	J	`jnl`	Adversarial Attacks on Stochastic Bandits. CoRR Kwang-Sung Jun, Lihong Li, Yuzhe Ma, Xiaojin Zhu
2018	—	`conf`	Data Poisoning Attacks in Contextual Bandits. GameSec Yuzhe Ma, Kwang-Sung Jun, Lihong Li, Xiaojin Zhu
2018	J	`jnl`	Data Poisoning Attacks in Contextual Bandits. CoRR Yuzhe Ma, Kwang-Sung Jun, Lihong Li, Xiaojin Zhu
2017	—	`conf`	Identifying Multiple Authors in a Binary Program. ESORICS (2) Xiaozhu Meng, Barton P. Miller, Kwang-Sung Jun
2017	A	`conf`	Improved Strongly Adaptive Online Learning using Coin Betting. AISTATS Kwang-Sung Jun, Francesco Orabona, Stephen J. Wright, Rebecca Willett
2017	J	`jnl`	Online Learning for Changing Environments using Coin Betting. CoRR Kwang-Sung Jun, Francesco Orabona, Stephen J. Wright, Rebecca Willett
2017	—	`conf`	Scalable Generalized Linear Bandits: Online Computation and Hashing. NIPS Kwang-Sung Jun, Aniruddha Bhargava, Robert D. Nowak, Rebecca Willett
2017	J	`jnl`	Scalable Generalized Linear Bandits: Online Computation and Hashing. CoRR Kwang-Sung Jun, Aniruddha Bhargava, Robert D. Nowak, Rebecca Willett
2016	A*	`conf`	Anytime Exploration for Multi-armed Bandits using Confidence Information. ICML Kwang-Sung Jun, Robert D. Nowak
2016	J	`jnl`	Graph-Based Active Learning: A New Look at Expected Error Minimization. CoRR Kwang-Sung Jun, Robert D. Nowak
2016	—	`conf`	Graph-based active learning: A new look at expected error minimization. GlobalSIP Kwang-Sung Jun, Robert D. Nowak
2016	J	`jnl`	Improved Strongly Adaptive Online Learning using Coin Betting. CoRR Kwang-Sung Jun, Francesco Orabona, Rebecca Willett, Stephen J. Wright
2016	A	`conf`	Top Arm Identification in Multi-Armed Bandits with Batch Arm Pulls. AISTATS Kwang-Sung Jun, Kevin Jamieson, Robert D. Nowak, Xiaojin Zhu
2016	B	`conf`	U-INVITE: Estimating Individual Semantic Networks from Fluency Data. CogSci Jeffrey C. Zemla, Yoed N. Kenett, Kwang-Sung Jun, Joseph L. Austerweil
2015	—	`conf`	Human Memory Search as Initial-Visit Emitting Random Walk. NIPS Kwang-Sung Jun, Xiaojin Zhu, Timothy T. Rogers, Zhuoran Yang, Ming Yuan
2013	—	`conf`	Learning from Human-Generated Lists. ICML (3) Kwang-Sung Jun, Xiaojin (Jerry) Zhu, Burr Settles, Timothy T. Rogers
2012	—	`conf`	Learning from Bullying Traces in Social Media. HLT-NAACL Jun-Ming Xu, Kwang-Sung Jun, Xiaojin Zhu, Amy Bellmore
2010	A*	`conf`	Cognitive Models of Test-Item Effects in Human Category Learning. ICML Xiaojin Zhu, Bryan R. Gibson, Kwang-Sung Jun, Timothy T. Rogers, Joseph Harrison, Chuck Kalish