Convergence rates for optimised adaptive importance samplers

DOI10.1007/S11222-020-09983-1zbMath1461.62010arXiv1903.12044OpenAlexW3125726451MaRDI QIDQ2029096

Ömer Deniz Akyildiz, Joaquín Míguez

Publication date: 3 June 2021

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1903.12044

zbMATH Keywords

convex optimizationimportance samplingvariational inferenceadaptive importance sampling

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08)

Related Items (9)

Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space ⋮ Daisee: Adaptive importance sampling by balancing exploration and exploitation ⋮ Gradient-based adaptive importance samplers ⋮ Efficient Bayes inference in neural networks through adaptive importance sampling ⋮ Context-Aware Surrogate Modeling for Balancing Approximation and Sampling Costs in Multifidelity Importance Sampling and Bayesian Inverse Problems ⋮ Variance analysis of multiple importance sampling schemes ⋮ Accelerated gradient methods for sparse statistical learning with nonconvex penalties ⋮ Implicitly adaptive importance sampling ⋮ MCMC-driven importance samplers

Cites Work

• Unnamed Item
• Unnamed Item
• Adaptive importance sampling for control and inference
• Particle-kernel estimation of the filter density in state-space models
• Minimizing finite sums with the stochastic average gradient
• Adaptive Monte Carlo variance reduction for Lévy processes with two-time-scale stochastic approximation
• Convergence of adaptive mixtures of importance sampling schemes
• Introductory lectures on convex optimization. A basic course.
• The sample size required in importance sampling
• Asymptotic bias of stochastic gradient search
• Importance sampling: intrinsic dimension and computational cost
• A framework for adaptive Monte Carlo procedures
• Importance Sampling and Necessary Sample Size: An Information Theory Approach
• Graphical Models, Exponential Families, and Variational Inference
• Optimizing Adaptive Importance Sampling by Stochastic Approximation
• Optimization Methods for Large-Scale Machine Learning
• Adaptative Monte Carlo Method, A Variance Reduction Technique
• Acceleration on Adaptive Importance Sampling with Sample Average Approximation
• A Stochastic Approximation Method

This page was built for publication: Convergence rates for optimised adaptive importance samplers