Trimming the Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning J Yun, P Zheng, E Yang, A Lozano, A Aravkin
International Conference on Machine Learning, 7242-7251, 2019
23 2019 Adaptive proximal gradient methods for structured neural networks J Yun, AC Lozano, E Yang
Advances in Neural Information Processing Systems 34, 24365-24378, 2021
16 2021 A general family of stochastic proximal gradient methods for deep learning J Yun, AC Lozano, E Yang
arXiv preprint arXiv:2007.07484, 2020
14 2020 Cluster-promoting quantization with bit-drop for minimizing network quantization loss JH Lee, J Yun, SJ Hwang, E Yang
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
11 2021 Adablock: SGD with practical block diagonal matrix adaptation for deep learning J Yun, A Lozano, E Yang
International Conference on Artificial Intelligence and Statistics, 2574-2606, 2022
3 2022 Stochastic gradient methods with block diagonal matrix adaptation J Yun, AC Lozano, E Yang
arXiv preprint arXiv:1905.10757, 2019
3 2019 M-estimation with the trimmed l1 penalty J Yun, P Zheng, E Yang, A Lozano, A Aravkin
arXiv preprint arXiv:1805.07495, 2018
3 2018 Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds J Yun, E Yang
Advances in Neural Information Processing Systems 36, 2024
2024 TEDDY: Trimming Edges with Degree-based Discrimination strategY H Seo, J Yun, E Yang
arXiv preprint arXiv:2402.01261, 2024
2024 TEDDY: Trimming Edges with Degree-based Graph Diffusion Strategy H Seo, J Yun, E Yang
The Twelfth International Conference on Learning Representations, 2023
2023 GradientMix: A Simple yet Effective Regularization for Large Batch Training J Yun, JH Lee, E Yang
2022