3 papers
cs.LG2026
Fast Log-Domain Sinkhorn Optimal Transport with Warp-Level GPU Reductions
Hao Xiao
Entropic regularized optimal transport (OT) via the Sinkhorn algorithm has become a fundamental tool in machine learning, yet existing implementations either suffer from numerical…
cs.LG2026
From Euler to Dormand-Prince: ODE Solvers for Flow Matching Generative Models
Hao Xiao
Sampling from Flow Matching generative models requires solving an ordinary differential equation (ODE) whose computational cost is dominated by neural network forward passes. We de…
cs.LG2026
Sparse Regression under Correlation and Weak Signals: A Reproducible Benchmark of Classical and Bayesian Methods
Hao Xiao
Choosing between classical and Bayesian sparse regression methods involves a real trade-off: penalized estimators like Lasso run in milliseconds but give no uncertainty estimates,w…