Picture for Zixiang Chen

Zixiang Chen

Benign Overfitting for Two-layer ReLU Networks

Mar 07, 2023
Yiwen Kou, Zixiang Chen, Yuanzhou Chen, Quanquan Gu

Figure 1 for Benign Overfitting for Two-layer ReLU Networks

Figure 2 for Benign Overfitting for Two-layer ReLU Networks

Figure 3 for Benign Overfitting for Two-layer ReLU Networks

Figure 4 for Benign Overfitting for Two-layer ReLU Networks

* 54 pages, 2 figures, 2 tables

Access Paper or Ask Questions

Learning High-Dimensional Single-Neuron ReLU Networks with Finite Samples

Mar 03, 2023
Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

Figure 1 for Learning High-Dimensional Single-Neuron ReLU Networks with Finite Samples

Figure 2 for Learning High-Dimensional Single-Neuron ReLU Networks with Finite Samples

Figure 3 for Learning High-Dimensional Single-Neuron ReLU Networks with Finite Samples

Figure 4 for Learning High-Dimensional Single-Neuron ReLU Networks with Finite Samples

* 41 pages, 4 figures

Access Paper or Ask Questions

Towards Understanding Mixture of Experts in Deep Learning

Aug 04, 2022
Zixiang Chen, Yihe Deng, Yue Wu, Quanquan Gu, Yuanzhi Li

Figure 1 for Towards Understanding Mixture of Experts in Deep Learning

Figure 2 for Towards Understanding Mixture of Experts in Deep Learning

Figure 3 for Towards Understanding Mixture of Experts in Deep Learning

Figure 4 for Towards Understanding Mixture of Experts in Deep Learning

* 53 pages, 8 figures, 11 tables

Access Paper or Ask Questions

Benign Overfitting in Two-layer Convolutional Neural Networks

Feb 14, 2022
Yuan Cao, Zixiang Chen, Mikhail Belkin, Quanquan Gu

Figure 1 for Benign Overfitting in Two-layer Convolutional Neural Networks

* 35 pages, 1 figure

Access Paper or Ask Questions

Faster Perturbed Stochastic Gradient Methods for Finding Local Minima

Oct 25, 2021
Zixiang Chen, Dongruo Zhou, Quanquan Gu

Figure 1 for Faster Perturbed Stochastic Gradient Methods for Finding Local Minima

Figure 2 for Faster Perturbed Stochastic Gradient Methods for Finding Local Minima

* 28 pages, 1 figure, 1 table

Access Paper or Ask Questions

Self-training Converts Weak Learners to Strong Learners in Mixture Models

Jul 16, 2021
Spencer Frei, Difan Zou, Zixiang Chen, Quanquan Gu

* 21 pages

Access Paper or Ask Questions

Almost Optimal Algorithms for Two-player Markov Games with Linear Function Approximation

Feb 15, 2021
Zixiang Chen, Dongruo Zhou, Quanquan Gu

* 31 pages

Access Paper or Ask Questions