3 papers
stat.ML2026
Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions
Di Wu, Ling Liang, Haizhao Yang
Bayesian Optimal Experimental Design (BOED) provides a rigorous framework for decision-making tasks in which data acquisition is often the critical bottleneck, especially in resour…
cs.LG2025
PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport
Di Wu, Ling Liang, Haizhao Yang
Optimal transport (OT) is a widely used tool in machine learning, but computing high-accuracy solutions for large instances remains costly. Entropic regularization and the Sinkhorn…
cs.LG2023
Neural Network Approximation for Pessimistic Offline Reinforcement Learning
Di Wu, Yuling Jiao, Li Shen +2
Deep reinforcement learning (RL) has shown remarkable success in specific offline decision-making scenarios, yet its theoretical guarantees are still under development. Existing wo…