Faster rates for convex-concave games J Abernethy, K Lai, K Levy, JK Wang Conference on Learning Theory, 2018 | 55 | 2018 |
Acceleration through optimistic no-regret dynamics JK Wang, JD Abernethy Advances in Neural Information Processing Systems 31, 2018 | 54 | 2018 |
On Frank-Wolfe and equilibrium computation JD Abernethy, JK Wang Advances in Neural Information Processing Systems 30, 2017 | 54 | 2017 |
A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network JK Wang, CH Lin, J Abernethy Proceedings of the 38th International Conference on Machine Learning, 2021 | 25 | 2021 |
No-regret dynamics in the fenchel game: A unified framework for algorithmic convex optimization JK Wang, J Abernethy, KY Levy Mathematical Programming 205 (1), 203-268, 2024 | 24 | 2024 |
Escaping saddle points faster with stochastic momentum JK Wang, CH Lin, J Abernethy International Conference on Learning Representations, 2020 | 20 | 2020 |
Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out JK Wang, CH Lin, A Wibisono, B Hu International Conference on Machine Learning, 2022 | 19 | 2022 |
Robust inverse covariance estimation under noisy measurements JK Wang International Conference on Machine Learning, 928-936, 2014 | 9 | 2014 |
Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation JK Wang, A Wibisono International Conference on Learning Representations, 2023 | 7 | 2023 |
Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time JK Wang, A Wibisono International Conference on Learning Representations, 2023 | 6 | 2023 |
An optimistic acceleration of amsgrad for nonconvex optimization JK Wang, X Li, B Karimi, P Li Asian Conference on Machine Learning, 422-437, 2021 | 6 | 2021 |
Revisiting projection-free optimization for strongly convex constraint sets J Rector-Brooks, JK Wang, B Mozafari Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 1576-1583, 2019 | 6 | 2019 |
Continuized Acceleration for Quasar Convex Functions in Non-Convex Optimization JK Wang, A Wibisono International Conference on Learning Representations, 2023 | 4 | 2023 |
Quickly finding a benign region via heavy ball momentum in non-convex optimization JK Wang, J Abernethy arXiv preprint arXiv:2010.01449, 2020 | 4 | 2020 |
Hamiltonian Descent and Coordinate Hamiltonian Descent JK Wang arXiv preprint arXiv:2402.13988, 2024 | 2 | 2024 |
Online linear optimization with sparsity constraints JK Wang, CJ Lu, SD Lin Algorithmic Learning Theory, 883-897, 2019 | 2 | 2019 |
Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron JK Wang, J Abernethy Asian Conference on Machine Learning, 17-32, 2021 | 1 | 2021 |
Parallel Least-Squares Policy Iteration JK Wang, SD Lin 2016 IEEE International Conference on Data Science and Advanced Analytics …, 2016 | 1 | 2016 |
Efficient Sampling-based ADMM for Distributed Data JK Wang, SD Lin 2016 IEEE International Conference on Data Science and Advanced Analytics …, 2016 | | 2016 |