CV

CV.pdf

Education

• Postdoctorate in University of Wisconsin at Madison, 2022 ~ Present
• Ph.D in The University of Texas at Austin, 2017 ~ 2022
• B.S. in Korea, Seoul National University (summa cum laude), 2016

Research experience

• Wisconsin Institute for Discovery, University of Wisconsin-Madison
  • Postdoctorate (with Prof. Robert Nowak)
• Decision, Information, and Communications Engineering (DICE), The University of Texas at Austin
  • Graduate Research Assistant (with Prof. Constantine Caramanis)
• Perceptron and Intelligence Laboratory (PIL), Seoul National University
  • Research Internship (with Prof. Jin Young Choi)

Work experience

• Alegion Inc., 2019.6 ~ 2019.8
  • Research Internship
  • Research on the automation of human annotation
• Scientific Analog, 2015.5 ~ 2016.6
  • Research and Development Engineer
  • Program Developer for Mixed Circuit Simulator
• Redduck, Inc., 2011.2 ~ 2013.12
  • PC Online Game Client Programmer

Publications

Future Prediction Can be a Strong Evidence of Good History Representation in Partially Observable Environments

J. Kwon, L. Yang, R. Nowak and J. Hanna
arXiv Preprint

On the Complexity of First-Order Methods in Stochastic Bilevel Optimization

J. Kwon, D. Kwon and H. Lyu
arXiv Preprint

Prospective Side Information for Latent MDPs

J. Kwon, Y. Efroni, C. Caramanis and S. Mannor
arXiv Preprint

On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation

J. Kwon, D. Kwon, S. Wright and R. Nowak
Proceedings of the 12th International Conference on Learning Representations (ICLR) 2024 (Spotlight)

A Fully First-Order Method for Stochastic Bilevel Optimization

J. Kwon, D. Kwon, S. Wright and R. Nowak
Proceedings of the 40th International Conference on Machine Learning (ICML) 2023 (Oral Presentation)

Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection

H. Bai, G. Canal, X. Du, J. Kwon, R. D Nowak, Y. Li
Proceedings of the 40th International Conference on Machine Learning (ICML) 2023

Reward-Mixing MDPs with Few Latent Contexts are Learnable

J. Kwon, Y. Efroni, C. Caramanis and S. Mannor
Proceedings of the 40th International Conference on Machine Learning (ICML) 2023

Tractable Optimality in Episodic Latent MABs

J. Kwon, Y. Efroni, C. Caramanis and S. Mannor
Proceedings of the 36th Neural Information Processing Systems (NeurIPS) 2022

Coordinate Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms

J. Kwon, Y. Efroni, C. Caramanis and S. Mannor
Proceedings of the 39th International Conference on Machine Learning (ICML) 2022

Reinforcement Learning in Reward-Mixing MDPs

J. Kwon, Y. Efroni, C. Caramanis and S. Mannor
Proceedings of the 35th Neural Information Processing Systems (NeurIPS) 2021

MLE and EM for Well-Separated Mixtures: Minimax Rates

J. Kwon and C. Caramanis
Work in Progress

RL for Latent MDPs: Regret Guarantees and a Lower Bound

J. Kwon, Y. Efroni, C. Caramanis and S. Mannor
Proceedings of the 35th Neural Information Processing Systems (NeurIPS) 2021 (Spotlight)

On the Computational and Statistical Complexity of Over-Parameterized Matrix Sensing

J. Zhuo, J. Kwon, N. Ho and C. Caramanis
Journal of Machine Learning Research (JMLR) 2024 (To appear)

On the Minimax Optimality of the EM Algorithm for Two-Component Mixed Linear Regression

J. Kwon, N. Ho and C. Caramanis
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021

The EM Algorithm gives Sample-Optimality for Learning Mixtures of Well-Separated Gaussians

J. Kwon and C. Caramanis
Proceedings of the 33rd Annual Conference on Learning Theory (COLT) 2020

EM Converges for a Mixture of Many Linear Regressions

J. Kwon and C. Caramanis
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS) 2020

Global Convergence of the EM Algorithm for Mixtures of Two Component Linear Regression

J. Kwon, W. Qian, C. Caramanis, Y. Chen, and D. Damek
Proceedings of the 32nd Annual Conference on Learning Theory (COLT) 2019

Skills

• Computer Skills: C/C++, Python, MATLAB, LaTeX
• Specialty: Learning Theory, Reinforcement Learning, Optimization, Algorithm
• Language: Korean (Native), English, Japanese