Optimization on Manifolds via Graph Gaussian Processes

DOI10.1137/22M1529907MaRDI QIDQ6151665zbMATH OpenOpenAlexFDO

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)

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

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)

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.

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

Cites work

• scientific article; zbMATH DE number 1223843 (Why is no real title available?)
• scientific article; zbMATH DE number 3210432 (Why is no real title available?)
• A brief introduction to manifold optimization
• An Introduction to Optimization on Smooth Manifolds
• An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach
• BART: Bayesian additive regression trees
• Bayesian optimization in a billion dimensions via random embeddings
• Bound-constrained global optimization of functions with low effective dimensionality using multiple random embeddings
• Continuum limits of posteriors in graph Bayesian inverse problems
• Diffusion maps
• Dispersion on a Sphere
• Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator
• Gaussian process landmarking on manifolds
• Gaussian processes for machine learning.
• Global optimization using random embeddings
• Graph Based Gaussian Processes on Restricted Domains
• Graph-based prior and forward models for inverse problems on manifolds with boundaries
• Inconsistent Estimation and Asymptotically Equal Interpolations in Model-Based Geostatistics
• Kernel Methods for Bayesian Elliptic Inverse Problems on Manifolds
• Local regularization of noisy point clouds: improved global geometric estimates and data analysis
• Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
• On the consistency of graph-based Bayesian semi-supervised learning and the scalability of sampling algorithms
• Optimization on flag manifolds
• Strictly and non-strictly positive definite functions on spheres
• The Geometry of Algorithms with Orthogonality Constraints
• The Rational SPDE Approach for Gaussian Random Fields With General Smoothness
• The SPDE approach to Matérn fields: graph representations

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)