 Dynamic Anisotropic Smoothing for Noisy Derivative-Free OptimizationInternational Conference on Machine Learning (ICML), 2024 |
 Sophia: A Scalable Stochastic Second-order Optimizer for Language Model
Pre-trainingInternational Conference on Learning Representations (ICLR), 2023 |
 Achieving High Accuracy with PINNs via Energy Natural GradientsInternational Conference on Machine Learning (ICML), 2023 |
 PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method
with Probabilistic Gradient EstimationInternational Conference on Machine Learning (ICML), 2022 |
