 A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded SmoothnessInternational Conference on Machine Learning (ICML), 2024 |
 An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded SmoothnessNeural Information Processing Systems (NeurIPS), 2024 |
 Revisiting Gradient Clipping: Stochastic bias and tight convergence
guaranteesInternational Conference on Machine Learning (ICML), 2023 |
 Variance-reduced Clipping for Non-convex OptimizationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 |
 EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections
for Federated Learning with Heterogeneous DataInternational Conference on Learning Representations (ICLR), 2023 |
