# Publications

### 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)

__[Arxiv]__ ### 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 (to appear)

__[Arxiv]__ ### 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

__[Arxiv]__ ### 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

__[Arxiv]__ __[Conference]__ ### 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

__[Arxiv]__ __[Conference]__ ### 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

__[Arxiv]__ __[Conference]__ ### MLE and EM for Well-Separated Mixtures: Minimax Rates

**J. Kwon** and C. Caramanis

Work in Progress

__[Arxiv]__ ### 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)

__[Arxiv]__ __[Conference]__ __[RL Theory Seminar]__ ### On the Computational and Statistical Complexity of Over-Parameterized Matrix Sensing

J. Zhuo, J. Kwon, N. Ho and C. Caramanis

Preprint, 2021

__[Arxiv]__ ### 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

__[Arxiv]__ __[Conference]__ ### 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

__[Arxiv]__ __[Conference]__ __[Video]__ ### 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

__[Arxiv]__ __[Conference]__ ### 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

__[Arxiv]__ __[Conference]__ __[Video]__