Li, Binghui

8 publications

ICLR 2026 Fast Catch-up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws Jinbo Wang, Binghui Li, Zhanpeng Zhou, Mingze Wang, Yuxuan Sun, Jiaqi Zhang, Xunliang Cai, Lei Wu

ICLR 2026 Larger Datasets Can Be Repeated More: A Theoretical Analysis of Multi-Epoch Scaling in Linear Regression Tingkai Yan, Haodong Wen, Binghui Li, Kairong Luo, Wenguang Chen, Kaifeng Lyu

ICLR 2025 Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data Binghui Li, Yuanzhi Li

ICLR 2025 Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks Binghui Li, Zhixuan Pan, Kaifeng Lyu, Jian Li

NeurIPS 2025 Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate Schedules Binghui Li, Fengling Chen, Zixun Huang, Lean Wang, Lei Wu

ICML 2025 On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics Binghui Li, Yuanzhi Li

NeurIPSW 2024 Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data Binghui Li, Yuanzhi Li

NeurIPS 2022 Why Robust Generalization in Deep Learning Is Difficult: Perspective of Expressive Power Binghui Li, Jikai Jin, Han Zhong, John Hopcroft, Liwei Wang