Repository: Freie Universit├Ąt Berlin, Math Department

Ensemble-based gradient inference for particle methods in optimization and sampling

Schillings, Claudia and Totzeck, Claudia and Wacker, Philipp (2022) Ensemble-based gradient inference for particle methods in optimization and sampling. ArXiv preprint . (Submitted)

Full text not available from this repository.

Official URL: https://doi.org/10.48550/arXiv.2209.15420

Abstract

We propose an approach based on function evaluations and Bayesian inference to extract higher-order differential information of objective functions {from a given ensemble of particles}. Pointwise evaluation of some potential in an ensemble contains implicit information about first or higher order derivatives, which can be made explicit with little computational effort (ensemble-based gradient inference -- EGI). We suggest to use this information for the improvement of established ensemble-based numerical methods for optimization and sampling such as Consensus-based optimization and Langevin-based samplers. Numerical studies indicate that the augmented algorithms are often superior to their gradient-free variants, in particular the augmented methods help the ensembles to escape their initial domain, to explore multimodal, non-Gaussian settings and to speed up the collapse at the end of optimization dynamics.} The code for the numerical examples in this manuscript can be found in the paper's Github repository (https://github.com/MercuryBench/ensemble-based-gradient.git). Claudia , Claudia , Philipp

Item Type:Article
Subjects:Mathematical and Computer Sciences > Mathematics > Applied Mathematics
Divisions:Department of Mathematics and Computer Science > Institute of Mathematics > Deterministic and Stochastic PDEs Group
ID Code:2982
Deposited By: Ulrike Eickers
Deposited On:22 May 2023 12:34
Last Modified:05 Jun 2023 12:03

Repository Staff Only: item control page