9 papers
Online Optimization of Difference-of-Convex Compositions with Smooth Mappings
Jingwei Ji, Jong-Shi Pang, Renyuan Xu
We study online optimization for a broad class of structured non-convex non-smooth problems where each loss is a composition of a difference-of-convex function with a smooth mappin…
Weak-to-Strong Learning in Decision Making
Jingwei Ji, Renyuan Xu
Many operational decisions rely on predictive models that estimate uncertain outcomes conditional on observable contexts. Training such models, however, often faces a fundamental d…
Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes
Hanqing Jin, Renyuan Xu, Yanzhao Yang
We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings th…
Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach
Zhengyi Guo, Wenpin Tang, Renyuan Xu
We study conditional generation in diffusion models under hard constraints, where generated samples must satisfy prescribed events with probability one. Such constraints arise natu…
One-Step Generative Modeling via Wasserstein Gradient Flows
Jiaqi Han, Puheng Li, Qiushan Guo +3
Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it requires many iterative updat…
Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization
Yinbin Han, Meisam Razaviyayn, Renyuan Xu
Diffusion models have become a leading paradigm in generative AI, with score estimation via denoising score matching as a central component. While recent theory provides strong sta…