Publications

Preprints

2024

A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
Junghyun Lee, Se-Young Yun, and Kwang-Sung Jun
In Neural Information Processing Systems (NeurIPS), 2024
Oral presentation at ICML’24 Workshop on Aligning Reinforcement Learning Experimentalists and Theorists
[arxiv]

Adaptive Experimentation When You Can't Experiment
Yao Zhao, Kwang-Sung Jun, Tanner Fiez, Lalit Jain
In Neural Information Processing Systems (NeurIPS), 2024
[arxiv]

Transfer Learning in Bandits with Latent Continuity
Hyejin Park, Seiyun Shin, Kwang-Sung Jun, Jungseul Ok
IEEE Transactions on Information Theory (TIT), 2024
[official]

Better-than-KL PAC-Bayes Bounds
Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona
In Conference on Learning Theory (COLT), 2024
[official] [arxiv]

Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits
Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun
In International Conference on Machine Learning (ICML), 2024
[official] [arxiv] [code] [video]

Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization
Kwang-Sung Jun, Jungtaek Kim
In International Conference on Machine Learning (ICML), 2024
[official] [arxiv]

Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
In International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
[official] [arxiv] [code]

Tight Concentrations and Confidence Sequences from the Regret of Universal Portfolio
Francesco Orabona, Kwang-Sung Jun
IEEE Transactions on Information Theory (TIT), 2024
[official] [arxiv]

2023

Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
Hao Qin, Kwang-Sung Jun, Chicheng Zhang
In Neural Information Processing Systems (NeurIPS), 2023
[official] [arxiv] [open review]

Revisiting Simple Regret: Fast Rates for Returning a Good Arm
Yao Zhao, Connor Stephens, Csaba Szepesvári, Kwang-Sung Jun
In International Conference on Machine Learning (ICML), 2023
[official] [arxiv]

Tighter PAC-Bayes Bounds Through Coin-Betting
Kyoungseok Jang, Kwang-Sung Jun, Ilja Kuzborskij, Francesco Orabona (alphabetical order)
In Conference on Learning Theory (COLT), 2023
Oral presentation at ICML’23 Workshop on PAC-Bayes Meets Interactive Learning
[official] [arxiv]

2022

PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits
Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun
In Neural Information Processing Systems (NeurIPS), 2022.
[official] [openreview] [arxiv]

Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs
Yeoneung Kim, Insoon Yang, Kwang-Sung Jun
In Neural Information Processing Systems (NeurIPS), 2022
[official] [openreview] [arxiv]

Jointly Efficient and Optimal Algorithms for Logistic Bandits
Louis Faury, Marc Abeille, Kwang-Sung Jun, Clément Calauzènes
In International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
[official] [arxiv]

Norm-Agnostic Linear Bandits
Spencer Brady Gales, Sunder Sethuraman, Kwang-Sung Jun
In International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
[official] [arxiv]

Maillard Sampling: Boltzmann Exploration Done Optimally
Jie Bian, Kwang-Sung Jun
In International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
[official] [arxiv]

An Experimental Design Approach for Regret Minimization in Logistic Bandits
Blake Mason, Kwang-Sung Jun, Lalit Jain
In AAAI Conference on Artificial Intelligence (AAAI), 2022
[official] [arxiv]

2021

Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits
Kwang-Sung Jun, Lalit Jain, Blake Mason, Houssam Nassif
In International Conference on Machine Learning (ICML), 2021
[official]

Improved Regret Bounds of Bilinear Bandits using Action Space Dimension Analysis
Kyoungseok Jang, Kwang-Sung Jun, Se Young Yun, Wanmo Kang
In International Conference on Machine Learning (ICML), 2021
[official]

Transfer Learning in Bandits with Latent Continuity
Hyejin Park, Seiyun Shin, Kwang-Sung Jun, Jungseul Ok
In IEEE International Symposium on Information Theory (ISIT), 2021
[official]

2020

Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality
Kwang-Sung Jun, Chicheng Zhang
In Neural Information Processing Systems (NeurIPS), 2020
[official] [arxiv] [slides] [video]

  • Previously appeared in ICML Workshop on Theoretical Foundations of Reinforcement Learning, 2020.

2019

Parameter-Free Locally Differentially Private Stochastic Subgradient Descent
Kwang-Sung Jun, Francesco Orabona
In NeurIPS Workshop on Privacy in Machine Learning (PriML), 2019
[arxiv] [poster]

Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration
Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona
In Neural Information Processing Systems (NeurIPS), 2019
[official] [arxiv] [slides] [poster]

Parameter-Free Online Convex Optimization with Sub-Exponential Noise
Kwang-Sung Jun, Francesco Orabona
In Conference on Learning Theory (COLT), 2019
[official] [arxiv]

Bilinear Bandits with Low-rank Structure
Kwang-Sung Jun, Rebecca Willett, Stephen Wright, Robert Nowak
In International Conference on Machine Learning (ICML), 2019
[official] [arxiv] [code]

2018

Adversarial Attacks on Stochastic Bandits
Kwang-Sung Jun, Lihong Li, Yuzhe Ma, Xiaojin Zhu
In Neural Information Processing Systems (NeurIPS), 2018
[official] [arxiv]

Data Poisoning Attacks in Contextual Bandits
Yuzhe Ma, Kwang-Sung Jun, Lihong Li, Xiaojin Zhu
In Conference on Decision and Game Theory for Security (GameSec), 2018
[official] [arxiv]

Bayesian Active Learning on Graphs
Kwang-Sung Jun, Robert Nowak
In Cooperative and Graph Signal Processing, Petar Djuric and Cedric Richard, Eds., Elsevier, 2018
[official]

2017

Online Learning for Changing Environments using Coin Betting
Kwang-Sung Jun, Francesco Orabona, Stephen Wright, Rebecca Willett
In Electronic Journal of Statistics (EJS), 2017
[official]

  • [conference version]
    Improved Strongly Adaptive Online Learning using Coin Betting
    Kwang-Sung Jun, Francesco Orabona, Stephen Wright, Rebecca Willett
    In International Conference on Artificial Intelligence and Statistics (AISTATS), 2017. Oral presentation
    [official] [arxiv]

Scalable Generalized Linear Bandits: Online Computation and Hashing
Kwang-Sung Jun, Aniruddha Bhargava, Robert Nowak, and Rebecca Willett
In Neural Information Processing Systems (NeurIPS), 2017
[official] [arxiv] [code]

Identifying Multiple Authors in a Binary Program
Xiaozhu Meng, Barton P. Miller, and Kwang-Sung Jun.
In European Symposium on Research in Computer Security (ESORICS), 2017
[official]

2016

Graph-Based Active Learning: A New Look at Expected Error Minimization.
Kwang-Sung Jun and Robert Nowak
In IEEE GlobalSIP Symposium on Non-Commutative Theory and Applications, 2016
[ieee] [arxiv]

U-INVITE: Estimating Individual Semantic Networks from Fluency Data
Jeffrey Zemla, Yoed Kenett, Kwang-Sung Jun, and Joseph Austerweil.
In Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci), 2016
[pdf]

Anytime Exploration for Multi-armed Bandits using Confidence Information
Kwang-Sung Jun and Robert Nowak
In International Conference on Machine Learning (ICML), 2016
[official] [post-publication note]

Top arm identification in multi-armed bandits with batch arm pulls.
Kwang-Sung Jun, Kevin Jamieson, Robert Nowak, and Xiaojin Zhu
In International Conference on Artificial Intelligence and Statistics (AISTATS), 2016
[official]

2015 and before

Human memory search as initial-visit emitting random walk.
Kwang-Sung Jun, Xiaojin Zhu, Timothy Rogers, Zhuoran Yang, and Ming Yuan.
In Neural Information Processing Systems (NeurIPS), 2015
[official]

Smarter Crisis Crowdsourcing.
Kayla Jacobs, Kwang-Sung Jun, Nathan Lieby, and Elena Eneva.
In ACM SIGKDD Workshop on Data Science for Social Good, 2014
[pdf]

Learning from Human-Generated Lists.
Kwang-Sung Jun, Xiaojin Zhu, Burr Settles, and Timothy Rogers
In International Conference on Machine Learning (ICML), 2013
[official] [code&data] [video]

An Image-To-Speech iPad App.
Michael Maynord, Jitrapon Tiachunpun, Xiaojin Zhu, Charles R. Dyer, Kwang-Sung Jun, and Jake Rosin.
Department of Computer Sciences Technical Report TR1774, University of Wisconsin-Madison, 2012.

Learning from bullying traces in social media.
Jun-Ming Xu, Kwang-Sung Jun, Xiaojin Zhu, and Amy Bellmore
In the Conference of North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT), 2012
[official]

With a little help from the computer: Hybrid human-machine systems on bandit problems
Bryan Gibson, Kwang-Sung Jun, and Xiaojin Zhu.
In NeurIPS Workshop on Computational Social Science and the Wisdom of Crowds, 2010.
[pdf]

Cognitive models of test-item effects in human category learning
Xiaojin Zhu, Bryan R. Gibson, Kwang-Sung Jun, Timothy T. Rogers, Joseph Harrison, and Chuck Kalish.
In International Conference on Machine Learning (ICML), 2010.
[acm digital library] [pdf]

An efficient collaborative filtering method based on k-nearest neighbor learning for large-scale data
Kwang-Sung Jun and Kyu-Baek Hwang.
In Proceedings of Korea Computer Congress, 2008.