Følg
Zhao Song
Zhao Song
Simons Institute for the Theory of Computing, UC Berkeley
Verifisert e-postadresse på ias.edu - Startside
Tittel
Sitert av
Sitert av
År
A convergence theory for deep learning via over-parameterization
Z Allen-Zhu, Y Li, Z Song
36th International Conference on Machine Learning (ICML), 242-252, 2019
17292019
Towards fast computation of certified robustness for relu networks
TW Weng, H Zhang, H Chen, Z Song, CJ Hsieh, D Boning, IS Dhillon, ...
35th International Conference on Machine Learning (ICML), 5273-5282, 2018
8342018
Solving linear programs in the current matrix multiplication time
MB Cohen, YT Lee, Z Song
Journal of the ACM (JACM) 68, 1--39, 2021
4532021
Solving linear programs in the current matrix multiplication time
MB Cohen, YT Lee, Z Song
51th Annual ACM Symposium on Theory of Computing (STOC), 938-942, 2019
4532019
Recovery guarantees for one-hidden-layer neural networks
K Zhong, Z Song, P Jain, PL Bartlett, IS Dhillon
34th International Conference on Machine Learning (ICML), 4140-4149, 2017
3712017
Evaluating gradient inversion attacks and defenses in federated learning
Y Huang, S Gupta, Z Song, K Li, S Arora
Advances in neural information processing systems 34, 7232-7241, 2021
3152021
H O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Z Zhang, Y Sheng, T Zhou, T Chen, L Zheng, R Cai, Z Song, Y Tian, C Ré, ...
NeurIPS 2023, 2023
3132023
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
Z Liu, J Wang, T Dao, T Zhou, B Yuan, Z Song, A Shrivastava, C Zhang, ...
ICML 2023, 2023
2652023
On the convergence rate of training recurrent neural networks
Z Allen-Zhu, Y Li, Z Song
Neural Information Processing Systems (NeurIPS), 6673-6685, 2019
2152019
The limitations of adversarial training and the blind-spot attack
H Zhang, H Chen, Z Song, D Boning, IS Dhillon, CJ Hsieh
The 7th International Conference on Learning Representations (ICLR), 2019
1862019
InstaHide: Instance-hiding Schemes for Private Distributed Learning
Y Huang, Z Song, K Li, S Arora
37th International Conference on Machine Learning (ICML), 2020
1712020
A Faster Interior Point Method for Semidefinite Programming
H Jiang, T Kathuria, YT Lee, S Padmanabhan, Z Song
61st Annual IEEE Symposium on Foundations of Computer Science (FOCS), 2020
1602020
Low rank approximation with entrywise -norm error
Z Song, DP Woodruff, P Zhong
49th Annual ACM Symposium on Theory of Computing (STOC), 688-701, 2017
1572017
Minimum Cost Flows, MDPs, and -Regression in Nearly Linear Time for Dense Instances
J van den Brand, Y Tat Lee, YP Liu, T Saranurak, A Sidford, Z Song, ...
53rd Annual ACM Symposium on Theory of Computing (STOC), 2021
1542021
Solving Empirical Risk Minimization in the Current Matrix Multiplication Time
YT Lee, Z Song, Q Zhang
Conference on Learning Theory (COLT), 2140-2157, 2019
1462019
Scatterbrain: Unifying Sparse and Low-rank Attention Approximation
B Chen, T Dao, E Winsor, Z Song, A Rudra, C Ré
NeurIPS 2021, 2021
144*2021
Relative error tensor low rank approximation
Z Song, DP Woodruff, P Zhong
30th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2772-2789, 2019
1362019
Faster dynamic matrix inverse for faster lps
S Jiang, Z Song, O Weinstein, H Zhang
53rd Annual ACM Symposium on Theory of Computing (STOC), 2021
1332021
An Improved Cutting Plane Method for Convex Optimization, Convex-Concave Games and its Applications
H Jiang, YT Lee, Z Song, SC Wong
52nd Annual ACM Symposium on Theory of Computing (STOC), 944-953, 2020
1322020
Bipartite Matching in Nearly-linear Time on Moderately Dense Graphs
J van den Brand, YT Lee, D Nanongkai, R Peng, T Saranurak, A Sidford, ...
61st Annual IEEE Symposium on Foundations of Computer Science (FOCS), 2020
1292020
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–20