Shuai Zhang

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 19

Top Topics

Number Of Hidden Units

Matrix Completion

Sample Complexity

Top Venues

Publications

Hongkang Li, Meng Wang, Shuai Zhang, Sijia Liu, Pin-Yu Chen
Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis. CoRR (2024)
Hongkang Li, Shuai Zhang, Yihua Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen
How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance. CoRR (2024)
Shuai Zhang, Heshan Devaka Fernando, Miao Liu, Keerthiram Murugesan, Songtao Lu, Pin-Yu Chen, Tianyi Chen, Meng Wang
SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning. CoRR (2024)
Shuai Zhang, Hongkang Li, Meng Wang, Miao Liu, Pin-Yu Chen, Songtao Lu, Sijia Liu, Keerthiram Murugesan, Subhajit Chaudhury
On the Convergence and Sample Complexity Analysis of Deep Q-Networks with ε-Greedy Exploration. CoRR (2023)
Mohammed Nowaz Rabbani Chowdhury, Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen
Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks. ICML (2023)
Shuai Zhang, Meng Wang, Pin-Yu Chen, Sijia Liu, Songtao Lu, Miao Liu
Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks. CoRR (2023)
Shuai Zhang, Meng Wang, Pin-Yu Chen, Sijia Liu, Songtao Lu, Miao Liu
Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks. ICLR (2023)
Hongkang Li, Shuai Zhang, Meng Wang
Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data. CoRR (2022)
Hongkang Li, Shuai Zhang, Meng Wang
Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data. CISS (2022)
Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong
How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis. ICLR (2022)
Shuai Zhang, Meng Wang, Jinjun Xiong, Sijia Liu, Pin-Yu Chen
Improved Linear Convergence of Training CNNs With Generalizability Guarantees: A One-Hidden-Layer Case. IEEE Trans. Neural Networks Learn. Syst. 32 (6) (2021)
Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong
Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks. NeurIPS (2021)
Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong
Guaranteed Convergence of Training Convolutional Neural Networks via Accelerated Gradient Descent. CISS (2020)
Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case. ICML (2020)
Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case. CoRR (2020)
Shuai Zhang, Meng Wang
Correction of Corrupted Columns Through Fast Robust Hankel Matrix Completion. IEEE Trans. Signal Process. 67 (10) (2019)
Shuai Zhang, Yingshuai Hao, Meng Wang, Joe H. Chow
Multichannel Hankel Matrix Completion Through Nonconvex Optimization. IEEE J. Sel. Top. Signal Process. 12 (4) (2018)
Shuai Zhang, Meng Wang
Correction of Simultaneous Bad Measurements by Exploiting the Low-rank Hankel Structure. ISIT (2018)
Shuai Zhang, Yingshuai Hao, Meng Wang, Joe H. Chow
Multi-Channel missing data recovery by exploiting the low-rank hankel structures. CAMSAP (2017)