Efficient sampling from time-varying log-concave distributions

MaRDI QIDQ4637035zbMATH OpenFDO

Authors Hariharan Narayanan, Alexander Rakhlin

Publication date 17 April 2018

Full work available at URL https://arxiv.org/abs/1309.5977, http://jmlr.csail.mit.edu/papers/v18/14-223.html

zbMATH Keywords

log-concave distributiontruncated distributions

Mathematics Subject Classification ID

Probability distributions: general theory (60E05) Sums of independent random variables; random walks (60G50) Learning and adaptive systems in artificial intelligence (68T05) Interior-point methods (90C51)

Recommendations

• Log-Sobolev inequalities and sampling from log-concave distributions
• The geometry of logconcave functions and sampling algorithms
• Sampling from log-concave distributions
• Randomized interior point methods for sampling and optimization
• Sampling from a log-concave distribution with projected Langevin Monte Carlo

Cites work

• A random polynomial-time algorithm for approximating the volume of convex bodies
• A sequential particle filter method for static models
• Adaptive Rejection Sampling for Gibbs Sampling
• An analog of the minimax theorem for vector payoffs
• Competitive On-line Statistics
• Concentration inequalities using the entropy method
• Finite mixture models
• Hit-and-run mixes fast
• scientific article; zbMATH DE number 3128728 (Why is no real title available?)
• scientific article; zbMATH DE number 3954145 (Why is no real title available?)
• scientific article; zbMATH DE number 729680 (Why is no real title available?)
• scientific article; zbMATH DE number 2117879 (Why is no real title available?)
• scientific article; zbMATH DE number 5019925 (Why is no real title available?)
• Inference and modeling with log-concave distributions
• Interior-Point Methods for Full-Information and Bandit Online Learning
• Interior-point methods for optimization
• Markov Chains and Stochastic Stability
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Model-Based Clustering, Discriminant Analysis, and Density Estimation
• On the Riemannian geometry defined by self-concordant barriers and interior-point methods.
• Prediction, Learning, and Games
• Random walks in a convex body and an improved volume algorithm
• Random walks on polytopes and an affine interior point method for linear programming
• Randomized interior point methods for sampling and optimization
• Relative loss bounds for on-line density estimation with the exponential family of distributions
• Ricci curvature of Markov chains on metric spaces
• Sampling from log-concave distributions
• Sequential Monte Carlo Methods in Practice
• Simulated Annealing for Convex Optimization
• Simulated annealing in convex bodies and an \(O^{*}(n^{4}\)) volume algorithm
• Some things we've learned (about Markov chain Monte Carlo)
• Stability properties of empirical risk minimization over Donsker classes
• The geometry of logconcave functions and sampling algorithms
• The Markov chain Monte Carlo revolution
• The weighted majority algorithm

Cited in

(4)

• Sampling from log-concave distributions
• Sampling from a log-concave distribution with projected Langevin Monte Carlo
• Sampling at a random time with a heavy-tailed distribution
• Dynamic inference in probabilistic graphical models

This page was built for publication: Efficient sampling from time-varying log-concave distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4637035)