Parallel sequential Monte Carlo for stochastic gradient-free nonconvex optimization

DOI10.1007/s11222-020-09964-4zbMath1452.62025arXiv1811.09469OpenAlexW3045675320MaRDI QIDQ2209727

Joaquín Míguez, Ömer Deniz Akyildiz, Dan Crisan

Publication date: 4 November 2020

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.09469

zbMATH Keywords

samplingstochastic optimizationnonconvex optimizationsequential Monte Carlogradient-free optimization

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Monte Carlo methods (65C05) Nonconvex programming, global optimization (90C26) Parallel numerical computation (65Y05)

Uses Software

• KernSmooth
• AdaGrad
• Adam
• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimization by Simulated Annealing
• Stochastic global optimization as a filtering problem
• Particle-kernel estimation of the filter density in state-space models
• On the convergence of two sequential Monte Carlo methods for maximum a posteriori sequence estimation and stochastic global optimization
• Analysis of a sequential Monte Carlo method for optimization in dynamical systems
• PRMLT
• Nested particle filters for online parameter estimation in discrete-time state-space Markov models
• Sequential Monte Carlo simulated annealing
• The landscape of empirical risk for nonconvex losses
• Nudging the particle filter
• Random gradient-free minimization of convex functions
• Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels
• Particle Filtering Framework for a Class of Randomized Optimization Algorithms
• Sequential Monte Carlo Samplers
• Introduction to Derivative-Free Optimization
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• A Survey of Some Model-Based Methods for Global Optimization
• Adapting the Number of Particles in Sequential Monte Carlo Methods Through an Online Scheme for Convergence Assessment
• Optimization Methods for Large-Scale Machine Learning
• On Accelerated Random Search
• Maslov Idempotent Probability Calculus, I
• Accelerated Stochastic Algorithms for Nonconvex Finite-Sum and Multiblock Optimization
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• A Stochastic Approximation Method
• On parallel implementation of sequential Monte Carlo methods: the island particle model