Nonlinear Bayesian optimal experimental design using logarithmic Sobolev inequalities
Not on the map. Why?
Abstract (arXiv)
We study the problem of selecting k experiments from a larger candidate pool, where the goal is to maximize mutual information (MI) between the selected subset and the underlying parameters. Finding the exact solution is to this combinatorial optimization problem is computationally costly, not only due to the complexity of the combinatorial search but also the difficulty of evaluating MI in nonlinear/non-Gaussian settings. We propose greedy approaches based on new computationally inexpensive lower bounds for MI, constructed via log-Sobolev inequalities. We demonstrate that our method outperforms random selection strategies, Gaussian approximations, and nested Monte Carlo (NMC) estimators of MI in various settings, including optimal design for nonlinear models with non-additive noise.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 23 Feb 2024.
Builds on
20 of 39 references.
References · 20
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
- 2019On Variational Bounds of Mutual Informationcited by 550
- 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
- 2019Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Sufficescited by 224
- 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
- 2019Variational Bayesian Optimal Experimental Designcited by 116
- 2017On Nesting Monte Carlo Estimatorscited by 82
- 2019A Unified Stochastic Gradient Approach to Designing Bayesian-Optimal Experimentscited by 58
- 2017Guarantees for Greedy Maximization of Non-submodular Functions with Applicationscited by 34
- 2021Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Boundscited by 26
- 2018Goal-Oriented Optimal Design of Experiments for Large-Scale Bayesian Linear Inverse Problemscited by 19
8 more
- 2014Algorithms for Approximate Minimization of the Difference Between Submodular Functions, with Applicationscited by 16
- 2013Curvature and Optimal Algorithms for Learning and Minimizing Submodular Functionscited by 12
- 2021Data-Free Likelihood-Informed Dimension Reduction of Bayesian Inverse Problemscited by 8
- 2013Fast Semidifferential-based Submodular Function Optimizationcited by 7
- 2021A Scalable Gradient-Free Method for Bayesian Experimental Design with Implicit Modelscited by 7
- 2020Batch greedy maximization of non-submodular functions: Guarantees and applications to experimental designcited by 4
- 2019Submodular Optimization Problems and Greedy Strategies: A Surveycited by 3
- 2014When do wireless network signals appear Poisson?cited by 2
Built on by
Citing papers per year: 2024: 2.
2 papers.