AI & ML
From Consensus-Based Optimization to Evolution Strategies: Proof of Global Convergence
arXiv cs.NA0 views
arXiv:2602.11677v3 Announce Type: replace-cross Abstract: Consensus-based optimization (CBO) is a powerful and versatile zero-order multi-particle method designed to provably solve high-dimensional global optimization problems, including those that are genuinely nonconvex or nonsmooth. The method relies on a balance between stochastic exploration and contraction toward a consensus point, which is defined via the Laplace principle as a proxy for the global minimizer. In this paper, we introduce new CBO variants that address practical and theoretical limitations of the original formulation of this novel optimization methodology. First, we propose a model called $\delta$-CBO}, which incorporates nonvanishing diffusion to prevent premature collapse to suboptimal states. We also develop a numerically stable implementation, the Consensus Freezing scheme, that remains robust even for arbitrarily large time steps by freezing the consensus point over time intervals. We connect these models through appropriate asymptotic limits. Furthermore, we derive from the Consensus Freezing scheme by suitable time rescaling and asymptotics a further algorithm, the Consensus Hopping scheme, which can be interpreted as a form of $(1,\lambda)$-Evolution Strategy. For all these schemes, we characterize for the first time the invariant measures and establish global convergence results, including exponential convergence rates.
Source:https://arxiv.org/abs/2602.11677PreviousUnconditionally $L^2$-stable explicit--implicit--null filtered Runge--Kutta methods for general nonlinear degenerate parabolic equationsNextFrom Defense to Advocacy: Empowering Users to Leverage the Blind Spot of AI Inference
Related posts
Razorpay webhook not verified: anyone can fake a payment
0dev.to
From FAQPage Schema to Answerable AI Documentation
0dev.to
Wiring Android's MediaPipe LLM Inference API to a Multi-Turn Conversation Engine
0dev.to
What Is LLM Throughput? Tokens per Second, Concurrency, and Batching
0dev.to
Diese Woche haben mir zwei Tools etwas vorgeschlagen und es direkt abgeschickt.
0dev.to
AI Agent Observability: What to Log Before Production
0dev.to