3 papers
stat.ML2026
Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
Guillaume Braun, Han Bao, Wei Huang +1
Spectral gradient methods, such as the Muon optimizer, modify gradient updates by preserving directional information while discarding scale, and have shown strong empirical perform…
cs.LG2026
Flow Matching from Viewpoint of Proximal Operators
Kenji Fukumizu, Wei Huang, Han Bao +2
We reformulate Optimal Transport Conditional Flow Matching (OT-CFM), a class of dynamical generative models, showing that it admits an exact proximal formulation via an extended Br…
stat.ML2026
Brenier Isotonic Regression
Han Bao, Amirreza Eshraghi, Yutong Wang
Isotonic regression (IR) is shape-constrained regression to maintain a univariate fitting curve non-decreasing, which has numerous applications including single-index models and pr…