Picture for Jingfeng Wu

Jingfeng Wu

Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability

May 19, 2023
Jingfeng Wu, Vladimir Braverman, Jason D. Lee

Figure 1 for Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability

Figure 2 for Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability

Access Paper or Ask Questions

Fixed Design Analysis of Regularization-Based Continual Learning

Mar 17, 2023
Haoran Li, Jingfeng Wu, Vladimir Braverman

Figure 1 for Fixed Design Analysis of Regularization-Based Continual Learning

Figure 2 for Fixed Design Analysis of Regularization-Based Continual Learning

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

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

Aug 03, 2022
Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

Figure 1 for The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

Figure 2 for The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

* 32 pages, 1 figure, 1 table

Access Paper or Ask Questions

Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime

Mar 07, 2022
Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

Figure 1 for Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime

Figure 2 for Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime

* 28 pages, 2 figures

Access Paper or Ask Questions

Gap-Dependent Unsupervised Exploration for Reinforcement Learning

Aug 11, 2021
Jingfeng Wu, Vladimir Braverman, Lin F. Yang

Figure 1 for Gap-Dependent Unsupervised Exploration for Reinforcement Learning

Figure 2 for Gap-Dependent Unsupervised Exploration for Reinforcement Learning

Access Paper or Ask Questions

The Benefits of Implicit Regularization from SGD in Least Squares Problems

Aug 10, 2021
Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Dean P. Foster, Sham M. Kakade

Figure 1 for The Benefits of Implicit Regularization from SGD in Least Squares Problems

* 39 pages, 1 figure

Access Paper or Ask Questions