Unbiased MLMC Stochastic Gradient-Based Optimization of Bayesian Experimental Designs
From MaRDI portal
Publication:5028414
DOI10.1137/20M1338848zbMath1484.62101arXiv2005.08414OpenAlexW3024572006MaRDI QIDQ5028414
Tomohiko Hironaka, Adam Foster, Takashi Goda, Wataru Kitade
Publication date: 9 February 2022
Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2005.08414
stochastic gradient descentmultilevel Monte CarloBayesian experimental designexpected information gainnested expectation
Optimal statistical designs (62K05) Monte Carlo methods (65C05) Kinetics in biochemical problems (pharmacokinetics, enzyme kinetics, etc.) (92C45) Stochastic approximation (62L20) Measures of information, entropy (94A17)
Related Items
Unbiased MLMC-based Variational Bayes for Likelihood-Free Inference ⋮ Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Multi-level stochastic approximation algorithms
- Multilevel simulation of functionals of Bernoulli random variables with application to basket credit derivatives
- Bayesian experimental design: A review
- Towards Bayesian experimental design for nonlinear models that require a large number of sampling times
- General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
- On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems
- Nesterov-aided stochastic gradient methods using Laplace approximation for Bayesian design optimization
- Fast Bayesian experimental design: Laplace-based importance sampling for the expected information gain
- Decision-making under uncertainty: using MLMC for efficient estimation of EVPPI
- A tutorial on adaptive design optimization
- Fast estimation of expected information gains for Bayesian experimental designs based on Laplace approximations
- Antithetic multilevel Monte Carlo estimation for multi-dimensional SDEs without Lévy area simulation
- Stochastic simulation: Algorithms and analysis
- Unbiased Estimation with Square Root Convergence for SDE Models
- Inverse problems: A Bayesian perspective
- Multilevel Monte Carlo Methods
- On a Measure of the Information Provided by an Experiment
- Multilevel Monte Carlo estimation of expected information gains
- Multilevel Monte Carlo Path Simulation
- Lectures on Stochastic Programming
- GRADIENT-BASED STOCHASTIC OPTIMIZATION METHODS IN BAYESIAN EXPERIMENTAL DESIGN
- Multilevel Monte Carlo Estimation of the Expected Value of Sample Information
- A Stochastic Approximation Method
