Yunwen Lei

Generalization and Optimization of SGD with Lookahead

Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification

Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness

Generalization Bounds for Rank-sparse Neural Networks

On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning