中文
相关论文

相关论文: Convergence of the kinetic annealing for general p…

200 篇论文

Combining classical arguments for the analysis of the simulated annealing algorithm with the more recent hypocoercive method of distorted entropy, we prove the convergence for large time of the kinetic Langevin annealing with logarithmic…

概率论 · 数学 2017-08-01 Pierre Monmarché

We study the simulated annealing algorithm based on the kinetic Langevin dynamics, in order to find the global minimum of a non-convex potential function. For both the continuous time formulation and a discrete time analogue, we obtain the…

概率论 · 数学 2022-06-14 Xuedong He , Xiaolu Tan , Ruocheng Wu

In this paper, we consider the generalised (higher order) Langevin equation for the purpose of simulated annealing and optimisation of nonconvex functions. Our approach modifies the underdamped Langevin equation by replacing the Brownian…

概率论 · 数学 2023-11-01 Martin Chak , Nikolas Kantas , Grigorios A. Pavliotis

We introduce a new probabilistic approach to quantify convergence to equilibrium for (kinetic) Langevin processes. In contrast to previous analytic approaches that focus on the associated kinetic Fokker-Planck equation, our approach is…

概率论 · 数学 2018-07-02 Andreas Eberle , Arnaud Guillin , Raphael Zimmer

Many practical samplers rely on time-dependent drifts -- often induced by annealing or tempering schedules -- to improve exploration and stability. This motivates a unified non-asymptotic analysis of the corresponding Langevin diffusions…

数值分析 · 数学 2026-05-12 Andreas Habring , Martin Zach

We consider a continuous analogue of the simulated annealing algorithm in $R^d$. We prove a convergence result, under hypotheses weaker than the usual ones. In particular, we cover cases where the gradient of the potential goes to zero at…

概率论 · 数学 2010-02-01 Pierre-André Zitt

We unify the variational hypocoercivity framework established by D. Albritton, S. Armstrong, J.-C. Mourrat, and M. Novack, with the notion of second-order lifts of reversible diffusion processes, recently introduced by A. Eberle and F.…

概率论 · 数学 2025-02-07 Giovanni Brigati , Francis Lörler , Lihan Wang

We study hypercontractivity for the underdamped Langevin dynamics with a convex confining potential. Unlike in the overdamped case, the noise acts only on the velocity variable, so the usual argument based on the logarithmic Sobolev…

偏微分方程分析 · 数学 2026-05-26 Bowen Li , Jianfeng Lu

We consider the global optimization of a non-convex potential $U : \mathbb{R}^d \to \mathbb{R}$ and extend the controlled simulated annealing framework introduced by Molin et al. (2026) to the class of swarm gradient dynamics, a family of…

最优化与控制 · 数学 2026-03-13 Louison Aubert

We consider Langevin dynamics associated with a modified kinetic energy vanishing for small momenta. This allows us to freeze slow particles, and hence avoid the re-computation of inter-particle forces, which leads to computational gains.…

统计力学 · 物理学 2016-07-20 Stephane Redon , Gabriel Stoltz , Zofia Trstanova

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, it seems to be a considerable restriction when the potentials are often required to be smooth (gradient Lipschitz). This paper…

统计计算 · 统计学 2022-02-23 Dao Nguyen

Convergence to equilibrium of underdamped Langevin dynamics is studied under general assumptions on the potential $U$ allowing for singularities. By modifying the direct approach to convergence in $L^2$ pioneered by F. H\'erau and…

概率论 · 数学 2022-01-19 Evan Camrud , David P. Herzog , Gabriel Stoltz , Maria Gordina

We present a modified simulated annealing method with a dynamical choice of the cooling temperature. The latter is determined via a closed-loop control and is proven to yield exponential decay of the entropy of the particle system. The…

最优化与控制 · 数学 2026-02-18 Michael Herty , Mattia Zanella

We provide a set of conditions which ensure the almost sure convergence of a class of simulated annealing algorithms on a bounded set $\mathcal{X}\subset\mathbb{R}^d$ based on a time-varying Markov kernel. The class of algorithms considered…

概率论 · 数学 2017-07-07 Mathieu Gerber , Luke Bornn

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler Maruyama discretization of the Langevin diffusion process, referred as Unadjusted Langevin Algorithm (ULA),…

统计计算 · 统计学 2021-07-28 Dao Nguyen , Xin Dang , Yixin Chen

Deep learning applications require global optimization of non-convex objective functions, which have multiple local minima. The same problem is often found in physical simulations and may be resolved by the methods of Langevin dynamics with…

机器学习 · 统计学 2021-05-24 Oleksandr Borysenko , Maksym Byshkin

We study three kinetic Langevin samplers including the Euler discretization, the BU and the UBU splitting scheme. We provide contraction results in $L^1$-Wasserstein distance for non-convex potentials. These results are based on a carefully…

概率论 · 数学 2025-08-20 Katharina Schuh , Peter A. Whalley

Given a target function $U$ to minimize on a finite state space $\mathcal{X}$, a proposal chain with generator $Q$ and a cooling schedule $T(t)$ that depends on time $t$, in this paper we study two types of simulated annealing (SA)…

概率论 · 数学 2020-07-21 Michael C. H. Choi

Explicit, momentum-based dynamics for optimizing functions defined on Lie groups was recently constructed, based on techniques such as variational optimization and left trivialization. We appropriately add tractable noise to the…

统计理论 · 数学 2024-06-19 Lingkai Kong , Molei Tao

We provide a framework to analyze the convergence of discretized kinetic Langevin dynamics for $M$-$\nabla$Lipschitz, $m$-convex potentials. Our approach gives convergence rates of $\mathcal{O}(m/M)$, with explicit stepsize restrictions,…

数值分析 · 数学 2024-05-24 Benedict Leimkuhler , Daniel Paulin , Peter A. Whalley
‹ 上一页 1 2 3 10 下一页 ›