AI RESEARCH
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
arXiv CS.LG
•
ArXi:2605.16520v1 Announce Type: new Sampling-based optimization (SBO), like cross-entropy method and evolutionary algorithms, has achieved many successes in solving non-convex problems without gradients, yet its convergence is poorly understood. In this paper, we establish a non-asymptotic convergence analysis for SBO through the lens of smoothing. Specifically, we recast SBO as gradient descent on a smoothed objective, mirroring noise-conditioned score ascent in diffusion models.