SOURCE-LINKED INTELLIGENCE

Fast PAC Global Optimization via Restarted Langevin: Exploration, Exploitation, and Degenerate Cooling

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

We study the computational effort required for global optimization of a smooth, possibly nonconvex objective $Γ:\mathbb{R}^d\to\mathbb{R}$. An algorithm satisfies the $(\varepsilon,δ)$-PAC performance requirement if its output $\widehat X$ obeys $\mathbb{P}\{Γ(\widehat X)-Γ^\star>\varepsilon\}\leqδ$. Algorithm design and analysis are in continuous time. We compare classical simulated annealing and fixed-temperature Langevin diffusion with two approaches introduced and analyzed here: parallel-restart Langevin and a Langevin--gradient scheme using stochastic dynamics for global exploration and g

Read original source ↗ Open in workspace

recordType

paper

region

Global