Principal feature detection via -Sobolev inequalities
DOI10.3150/23-BEJ1702zbMATH Open1545.68121MaRDI QIDQ6589581FDOQ6589581
Authors: Matthew T. C. Li, Youssef M. Marzouk, Olivier Zahm 
Publication date: 20 August 2024
Published in: Bernoulli (Search for Journal in Brave)
Recommendations
- Kullback-Leibler approximation for probability measures on infinite dimensional spaces
- Certified Dimension Reduction for Bayesian Updating with the Cross-Entropy Method
- Algorithms for Kullback-Leibler approximation of probability measures in infinite dimensions
- Gaussian approximations for probability measures on \(\mathbb R^d\)
- Mean field approximations via log-concavity
principal componentsBayesian inferencefeature detection\( \phi \)-Sobolev inequalitiesAmari \(\alpha \)-divergencesgradient-based dimension reduction
Bayesian inference (62F15) Factor analysis and principal components; correspondence analysis (62H25) Computational aspects of data analysis and big data (68T09) Pattern recognition, speech recognition (68T10) Measures of information, entropy (94A17) Inequalities involving derivatives and differential and integral operators (26D10)
Cites Work
- Sequential Monte Carlo Samplers
- Statistical and computational inverse problems.
- Foundations of Modern Probability
- Title not available (Why is that?)
- Can local particle filters beat the curse of dimensionality?
- Optimal Scaling of Discrete Approximations to Langevin Diffusions
- General state space Markov chains and MCMC algorithms
- Exploring Regression Structure Using Nonparametric Functional Estimation
- Inverse problems: a Bayesian perspective
- A logarithmic Sobolev form of the Li-Yau parabolic inequality
- On Divergences and Informations in Statistics and Information Theory
- A Generalized Poincare Inequality for Gaussian Measures
- Title not available (Why is that?)
- Transportation-information inequalities for Markov processes
- Entropies, convexity, and functional inequalities: on \(\Phi\)-entropies and \(\Phi\)-Sobolev inequalities
- Analysis and geometry of Markov diffusion operators
- Hypercontractivity and logarithmic Sobolev inequalities for the Clifford- Dirichlet form
- MCMC methods for functions: modifying old algorithms to make them faster
- On the Optimality of Conditional Expectation as a Bregman Predictor
- $\alpha$-Divergence Is Unique, Belonging to Both $f$-Divergence and Bregman Divergence Classes
- Phi-entropy inequalities for diffusion semigroups
- Title not available (Why is that?)
- Nonlinear dimension reduction for surrogate modeling using gradient information
- Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
- Active subspaces. Emerging ideas for dimension reduction in parameter studies
- Likelihood-informed dimension reduction for nonlinear inverse problems
- On a generalization of the preconditioned Crank-Nicolson metropolis algorithm
- Dimension-independent likelihood-informed MCMC
- Optimal low-rank approximations of Bayesian linear inverse problems
- A Family of Nonparametric Density Estimation Algorithms
- On Pairs of $f$-Divergences and Their Joint Range
- Certified dimension reduction in nonlinear Bayesian inverse problems
- Data-free likelihood-informed dimension reduction of Bayesian inverse problems
- Geometric MCMC for infinite-dimensional inverse problems
- Accelerating Markov chain Monte Carlo with active subspaces
- Gradient-based dimension reduction of multivariate vector-valued functions
- Cross-Entropy-Based Importance Sampling with Failure-Informed Dimension Reduction for Rare Event Simulation
- Large Deviation Theory-based Adaptive Importance Sampling for Rare Events in High Dimensions
- A unified performance analysis of likelihood-informed subspace methods
- Modified Active Subspaces Using the Average of Gradients
- Prior normalization for certified likelihood-informed subspace detection of Bayesian inverse problems
- Preintegration via Active Subspace
- Certified Dimension Reduction for Bayesian Updating with the Cross-Entropy Method
- Scalable conditional deep inverse Rosenblatt transports using tensor trains and gradient-based dimension reduction
- hIPPYlib-MUQ: a Bayesian inference software framework for integration of data with complex predictive models under uncertainty
- Rapid convergence of the unadjusted Langevin algorithm: isoperimetry suffices
This page was built for publication: Principal feature detection via \(\phi \)-Sobolev inequalities
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6589581)
