Optimization on Manifolds via Graph Gaussian Processes

DOI10.1137/22M1529907arXiv2210.10962OpenAlexW4391476838MaRDI QIDQ6151665FDOQ6151665

Authors: Hwanwoo Kim, Daniel Sanz-Alonso, Ruiyi Yang 

Publication date: 12 February 2024

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Abstract: This paper integrates manifold learning techniques within a emph{Gaussian process upper confidence bound} algorithm to optimize an objective function on a manifold. Our approach is motivated by applications where a full representation of the manifold is not available and querying the objective is expensive. We rely on a point cloud of manifold samples to define a graph Gaussian process surrogate model for the objective. Query points are sequentially chosen using the posterior distribution of the surrogate model given all previous queries. We establish regret bounds in terms of the number of queries and the size of the point cloud. Several numerical examples complement the theory and illustrate the performance of our method.

Full work available at URL: https://arxiv.org/abs/2210.10962

Recommendations

• Gaussian process bandits with adaptive discretization
• Bayesian optimization
• Deep Gaussian process for multi-objective Bayesian optimization
• Optimal learning with a local parametric belief model
• Convergence rates of efficient global optimization algorithms

zbMATH Keywords

manifold learningBayesian optimizationgraph Gaussian processes

Mathematics Subject Classification ID

Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05) Gaussian processes (60G15) Graph algorithms (graph-theoretic aspects) (05C85) Nonconvex programming, global optimization (90C26)

Cites Work

• BART: Bayesian additive regression trees
• The Rational SPDE Approach for Gaussian Random Fields With General Smoothness
• Diffusion maps
• Bayesian optimization in a billion dimensions via random embeddings
• Gaussian processes for machine learning.
• Strictly and non-strictly positive definite functions on spheres
• Title not available (Why is that?)
• Inconsistent Estimation and Asymptotically Equal Interpolations in Model-Based Geostatistics
• An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach
• Title not available (Why is that?)
• The Geometry of Algorithms with Orthogonality Constraints
• Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
• Dispersion on a Sphere
• Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator
• The SPDE approach to Matérn fields: graph representations
• A brief introduction to manifold optimization
• Continuum limits of posteriors in graph Bayesian inverse problems
• Local regularization of noisy point clouds: improved global geometric estimates and data analysis
• Kernel Methods for Bayesian Elliptic Inverse Problems on Manifolds
• On the consistency of graph-based Bayesian semi-supervised learning and the scalability of sampling algorithms
• Optimization on flag manifolds
• Gaussian process landmarking on manifolds
• An Introduction to Optimization on Smooth Manifolds
• Bound-constrained global optimization of functions with low effective dimensionality using multiple random embeddings
• Graph Based Gaussian Processes on Restricted Domains
• Graph-based prior and forward models for inverse problems on manifolds with boundaries
• Global optimization using random embeddings

This page was built for publication: Optimization on Manifolds via Graph Gaussian Processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6151665)