Xuran Meng

According to our database, Xuran Meng authored at least 6 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Multiple Descent in the Multiple Random Feature Model.

Xuran Meng, Jianfeng Yao, Yuan Cao

J. Mach. Learn. Res., 2024

Initialization Matters: On the Benign Overfitting of Two-Layer ReLU CNN with Fully Trainable Layers.

Shuning Shang, Xuran Meng, Yuan Cao, Difan Zou

CoRR, 2024

Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data.

Xuran Meng, Difan Zou, Yuan Cao

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping.

Xuran Meng, Jeff Yao

J. Mach. Learn. Res., 2023

Per-Example Gradient Regularization Improves Learning Signals from Noisy Data.

Xuran Meng, Yuan Cao, Difan Zou

CoRR, 2023

2021

Implicit Data-Driven Regularization in Deep Neural Networks under SGD.

Xuran Meng, Jianfeng Yao

CoRR, 2021