Paper-Conference | Chenghan Xie | Stanford Operations Research Ph.D. Student

Sobolev Regularized Score Difference Estimation in Diffusion Models

Fri, 01 May 2026 00:00:00 +0000

We propose a Sobolev-regularized classification framework for score difference estimation in diffusion models, resolving gradient divergence issues in standard transfer learning. The method improves ECG generation from PTB-XL to ICBEB2018 and achieves stronger robustness in small-sample regimes.

Sketched Newton Value Iteration for Large-Scale Markov Decision Processes

Fri, 01 Mar 2024 00:00:00 +0000

Trust Region Methods for Nonconvex Stochastic Optimization beyond Lipschitz Smoothness

Fri, 01 Mar 2024 00:00:00 +0000

This AAAI 2024 paper studies stochastic nonconvex optimization beyond the standard globally Lipschitz-gradient assumption. It analyzes trust-region methods under a generalized smoothness setting motivated by deep learning and distributionally robust optimization, showing how first-order trust-region methods unify normalized and clipped stochastic-gradient updates and how second-order variants can obtain stronger stationarity guarantees with variance reduction.