← Search

Chenguang Duan

2 accepted papers

2025

Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees

NeurIPS 2025poster

Learning transferable data representations from abundant unlabeled data remains a central challenge in machine learning. Although numerous self-supervised learning methods have been proposed to address this challenge, a significant class of these approaches aligns the covariance or correlation matri…

Cited by 0SourceScholar
2023

Fast Excess Risk Rates via Offset Rademacher Complexity

ICML 2023poster

Based on the offset Rademacher complexity, this work outlines a systematical framework for deriving sharp excess risk bounds in statistical learning without Bernstein condition. In addition to recovering fast rates in a unified way for some parametric and nonparametric supervised learning models wit…

Cited by 5SourcePDFScholar