Showing results 1 to 7 of 7
AdaBlock: SGD with Practical Block Diagonal Matrix Adaptation for Deep Learning Yun, Jihun; Lozano, Aurelie C.; Yang, Eunho, International Conference on Artificial Intelligence and Statistics, JMLR-JOURNAL MACHINE LEARNING RESEARCH, 2022-03 |
Adaptive Proximal Gradient Methods for Structured Neural Networks Yun, Jihun; Aurelie, Lozano; Yang, Eunho, 35th Conference on Neural Information Processing Systems (NeurIPS), Neural Information Processing Systems, 2021-12-10 |
Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss Lee, Jung Hyun; Yun, Jihun; Hwang, Sung Ju; Yang, Eunho, 18th IEEE/CVF International Conference on Computer Vision (ICCV), pp.5370 - 5379, Computer Vision Foundation, IEEE Computer Society, 2021-10-14 |
Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds Yun, Jihun; Yang, Eunho, 37th Conference on Neural Information Processing Systems, NeurIPS 2023, Neural Information Processing Systems, 2023-12-13 |
TEDDY: Trimming Edges with Degree-based Discrimination strategY Seo, Hyunjin; Yun, Jihun; Yang, Eunho, The Twelfth International Conference on Learning Representations, ICLR 2024, International Conference on Learning Representations (ICLR), 2024-05-09 |
Trimming the $l_1$ regularizer : statistical analysis, optimization, and applications to deep learning = 가지친 $l_1$ 정규화 : 통계적 이론 분석, 최적화, 그리고 딥러닝 문제에 대한 적용 방법link Yun, Jihun; Yang, Eunho; et al, 한국과학기술원, 2020 |
Trimming the l-1 Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning Yun, Jihun; Zheng, Peng; Yang, Eunho; Lozano, Aurelie; Aravkin Aleksandr, Thirty-sixth International Conference on Machine Learning, ICML, 2019-06-10 |
Discover