3 papers
stat.ML2026
Robust Diffusion Models via Divergence-Induced Weighted Denoising
Lei Li, Yuexiao Dong
We show that replacing the standard MSE denoising loss in diffusion models with a nonlinear transformation induced by an f-divergence yields a simple robust training surrogate that…
stat.ME2026
Probabilistic Win Ratio Method For Hierarchical Composite Endpoints With Coarsened Outcomes
Lei Li, Jing Lei, Yuexiao Dong
The win ratio is increasingly used to analyze prioritized composite endpoints in clinical trials, but standard implementations rely on deterministic pairwise comparisons and can pe…
stat.ME2024
Sufficient dimension reduction for regression with metric space-valued responses
Abdul-Nasah Soale, Yuexiao Dong
Data visualization and dimension reduction for regression between a general metric space-valued response and Euclidean predictors is proposed. Current Fréchét dimension reduction…