RL for latent MDPs: Regret guarantees and a lower bound J Kwon, Y Efroni, C Caramanis, S Mannor Advances in Neural Information Processing Systems 34, 24523-24534, 2021 | 77 | 2021 |
Global convergence of the EM algorithm for mixtures of two component linear regression J Kwon, W Qian, C Caramanis, Y Chen, D Davis Conference on Learning Theory, 2055-2110, 2019 | 74 | 2019 |
EM converges for a mixture of many linear regressions J Kwon, C Caramanis International Conference on Artificial Intelligence and Statistics, 1727-1736, 2020 | 46 | 2020 |
A fully first-order method for stochastic bilevel optimization J Kwon, D Kwon, S Wright, RD Nowak International Conference on Machine Learning, 18083-18113, 2023 | 43 | 2023 |
On the minimax optimality of the EM algorithm for learning two-component mixed linear regression J Kwon, N Ho, C Caramanis International Conference on Artificial Intelligence and Statistics, 1405-1413, 2021 | 43 | 2021 |
The EM algorithm gives sample-optimality for learning mixtures of well-separated gaussians J Kwon, C Caramanis Conference on Learning Theory, 2425-2487, 2020 | 35* | 2020 |
On the computational and statistical complexity of over-parameterized matrix sensing J Zhuo, J Kwon, N Ho, C Caramanis Journal of Machine Learning Research 25 (169), 1-47, 2024 | 32 | 2024 |
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, RD Nowak, Y Li International Conference on Machine Learning, 1454-1471, 2023 | 20 | 2023 |
Reinforcement learning in reward-mixing MDPs J Kwon, Y Efroni, C Caramanis, S Mannor Advances in Neural Information Processing Systems 34, 2253-2264, 2021 | 20 | 2021 |
On penalty methods for nonconvex bilevel optimization and first-order stochastic approximation J Kwon, D Kwon, S Wright, R Nowak arXiv preprint arXiv:2309.01753, 2023 | 14 | 2023 |
Coordinated attacks against contextual bandits: Fundamental limits and defense mechanisms J Kwon, Y Efroni, C Caramanis, S Mannor International Conference on Machine Learning, 11772-11789, 2022 | 8 | 2022 |
Reward-mixing MDPs with few latent contexts are learnable J Kwon, Y Efroni, C Caramanis, S Mannor International Conference on Machine Learning, 18057-18082, 2023 | 6 | 2023 |
Prospective side information for latent MDPs J Kwon, Y Efroni, S Mannor, C Caramanis arXiv preprint arXiv:2310.07596, 2023 | 3 | 2023 |
Tractable optimality in episodic latent MABs J Kwon, Y Efroni, C Caramanis, S Mannor Advances in Neural Information Processing Systems 35, 23634-23645, 2022 | 3 | 2022 |
On the complexity of first-order methods in stochastic bilevel optimization J Kwon, D Kwon, H Lyu arXiv preprint arXiv:2402.07101, 2024 | 2 | 2024 |
Statistical learning with latent variables: mixture models and reinforcement learning J Kwon | 1 | 2022 |
Power Loss Analysis of Switched-mode Converter Circuits in XMODEL Y Lee, J Kwon, J Kim IEICE Proceedings Series 61 (5174), 2016 | 1 | 2016 |
Modeling and simulation of nonlinear transient responses of high-voltage wordline generators in NAND flash memories J Lee, JY Kwon, J Kim 2015 International SoC Design Conference (ISOCC), 323-324, 2015 | 1 | 2015 |
Global Optimality of the EM Algorithm for Mixtures of Two-Component Linear Regressions J Kwon, W Qian, Y Chen, C Caramanis, D Davis, N Ho IEEE Transactions on Information Theory, 2024 | | 2024 |
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation J Kwon, S Mannor, C Caramanis, Y Efroni arXiv preprint arXiv:2406.01389, 2024 | | 2024 |