Continuum Limits of Posteriors in Graph Bayesian Inverse Problems

DOI10.1137/17M1138005zbMath1416.28003arXiv1706.07193OpenAlexW2963266525WikidataQ129511905 ScholiaQ129511905MaRDI QIDQ3176426

Nicolás García Trillos, Daniel Sanz-Alonso

Publication date: 20 July 2018

Published in: SIAM Journal on Mathematical Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1706.07193

zbMATH Keywords

heat equationmachine learningBayesian inverse problemgraph Laplacian

Mathematics Subject Classification ID

Bayesian inference (62F15) Spaces of measures, convergence of measures (28A33) Applications of functional analysis in probability theory and statistics (46N30)

Related Items (20)

A Maximum Principle Argument for the Uniform Convergence of Graph Laplacian Regressors ⋮ Lipschitz Regularity of Graph Laplacians on Random Data Clouds ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Convergence theorems for varying measures under convexity conditions and applications ⋮ Rates of convergence for Laplacian semi-supervised learning with low labeling rates ⋮ Unnamed Item ⋮ Analysis of a Computational Framework for Bayesian Inverse Problems: Ensemble Kalman Updates and MAP Estimators under Mesh Refinement ⋮ Optimization on Manifolds via Graph Gaussian Processes ⋮ Kernel Methods for Bayesian Elliptic Inverse Problems on Manifolds ⋮ Asymptotic spectra of large (grid) graphs with a uniform local structure. I: Theory ⋮ The Bayesian update: variational formulations and gradient flows ⋮ Fatou's Lemma for Weakly Converging Measures under the Uniform Integrability Condition ⋮ Data-driven forward discretizations for Bayesian inversion ⋮ Analysis of stochastic gradient descent in continuous time ⋮ Analysis of $p$-Laplacian Regularization in Semisupervised Learning ⋮ Convergence for varying measures ⋮ The SPDE approach to Matérn fields: graph representations ⋮ Variational Limits of $k$-NN Graph-Based Functionals on Data Clouds ⋮ Graph-based prior and forward models for inverse problems on manifolds with boundaries

Cites Work

• Unnamed Item
• Unnamed Item
• Continuum limit of total variation on point clouds
• Gamma-convergence of gradient flows on Hilbert and metric spaces and applications
• Importance sampling: intrinsic dimension and computational cost
• A graph discretization of the Laplace-Beltrami operator
• Inverse problems: A Bayesian perspective
• Large‐Scale Inverse Problems and Quantification of Uncertainty
• Uncertainty Quantification and Weak Approximation of an Elliptic Inverse Problem
• Uncertainty Quantification in Graph-Based Classification of High Dimensional Data
• On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
• Bayesian inverse problems for functions and applications to fluid mechanics
• The Bayesian formulation and well-posedness of fractional elliptic inverse problems
• Fatou's Lemma for Weakly Converging Probabilities
• On the heat flow on metric measure spaces: existence, uniqueness and stability

This page was built for publication: Continuum Limits of Posteriors in Graph Bayesian Inverse Problems