Implicitly adaptive importance sampling
From MaRDI portal
Publication:2058716
DOI10.1007/S11222-020-09982-2zbMATH Open1475.62053arXiv1906.08850OpenAlexW3022123134MaRDI QIDQ2058716FDOQ2058716
Authors: Topi Paananen, Juho Piironen, Paul-Christian Bürkner, Aki Vehtari 
Publication date: 9 December 2021
Published in: Statistics and Computing (Search for Journal in Brave)
Abstract: Adaptive importance sampling is a class of techniques for finding good proposal distributions for importance sampling. Often the proposal distributions are standard probability distributions whose parameters are adapted based on the mismatch between the current proposal and a target distribution. In this work, we present an implicit adaptive importance sampling method that applies to complicated distributions which are not available in closed form. The method iteratively matches the moments of a set of Monte Carlo draws to weighted moments based on importance weights. We apply the method to Bayesian leave-one-out cross-validation and show that it performs better than many existing parametric adaptive importance sampling methods while being computationally inexpensive.
Full work available at URL: https://arxiv.org/abs/1906.08850
Recommendations
Cites Work
- Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC
- The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
- Bayesian model averaging: A tutorial. (with comments and a rejoinder).
- The sample size required in importance sampling
- A survey of Bayesian predictive methods for model assessment, selection and comparison
- Case-deletion importance sampling estimators: central limit theorems and related results
- Comparison of Bayesian predictive methods for model selection
- A Predictive Approach to Model Selection
- Title not available (Why is that?)
- On the Variability of Case-Deletion Importance Sampling Weights in the Bayesian Linear Model
- Bayesian Model Assessment and Comparison Using Cross-Validation Predictive Densities
- Strictly Proper Scoring Rules, Prediction, and Estimation
- Title not available (Why is that?)
- Title not available (Why is that?)
- Sparsity information and regularization in the horseshoe and other shrinkage priors
- General state space Markov chains and MCMC algorithms
- Expected information as ecpected utility
- Weighted Average Importance Sampling and Defensive Mixture Distributions
- Adaptive Multiple Importance Sampling
- Nonparametric Importance Sampling
- Safe and Effective Importance Sampling
- Adaptive importance sampling for control and inference
- Methods of Reducing Sample Size in Monte Carlo Computations
- Rare Event Simulation using Monte Carlo Methods
- Expectation propagation in linear regression models with spike-and-slab priors
- Convergence rates for optimised adaptive importance samplers
- A population Monte Carlo scheme with transformed weights and its application to stochastic kinetic models
- Generalized multiple importance sampling
- An Adaptive Population Importance Sampler: Learning From Uncertainty
Cited In (14)
- Unconstrained recursive importance sampling
- Title not available (Why is that?)
- Projective inference in high-dimensional problems: prediction and feature selection
- Mixing artificial and natural intelligence: from statistical mechanics to AI and back to turbulence
- Policy Gradient Importance Sampling for Bayesian Inference
- Gradient-based adaptive importance samplers
- Daisee: Adaptive importance sampling by balancing exploration and exploitation
- Adaptive multiple importance sampling for Gaussian processes
- Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
- Robust Leave-One-Out Cross-Validation for High-Dimensional Bayesian Models
- Large Deviation Theory-based Adaptive Importance Sampling for Rare Events in High Dimensions
- Detecting and diagnosing prior and likelihood sensitivity with power-scaling
- Adapative importance sampling on discrete Markov chains
- Quantization based recursive importance sampling
This page was built for publication: Implicitly adaptive importance sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2058716)
