CO-BED: Information-Theoretic Contextual Optimization via Bayesian
Experimental Design
- URL: http://arxiv.org/abs/2302.14015v1
- Date: Mon, 27 Feb 2023 18:14:13 GMT
- Title: CO-BED: Information-Theoretic Contextual Optimization via Bayesian
Experimental Design
- Authors: Desi R. Ivanova, Joel Jennings, Tom Rainforth, Cheng Zhang, Adam
Foster
- Abstract summary: CO-BED is a model-agnostic framework for designing contextual experiments using information-theoretic principles.
As a result, CO-BED provides a general and automated solution to a wide range of contextual optimization problems.
- Score: 31.247108087199095
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We formalize the problem of contextual optimization through the lens of
Bayesian experimental design and propose CO-BED -- a general, model-agnostic
framework for designing contextual experiments using information-theoretic
principles. After formulating a suitable information-based objective, we employ
black-box variational methods to simultaneously estimate it and optimize the
designs in a single stochastic gradient scheme. We further introduce a
relaxation scheme to allow discrete actions to be accommodated. As a result,
CO-BED provides a general and automated solution to a wide range of contextual
optimization problems. We illustrate its effectiveness in a number of
experiments, where CO-BED demonstrates competitive performance even when
compared to bespoke, model-specific alternatives.
Related papers
- Optimizing Likelihoods via Mutual Information: Bridging Simulation-Based Inference and Bayesian Optimal Experimental Design [0.0]
gradient-based BOED methods have been proposed as an alternative to Bayesian optimization and other experimental designs.
We show a link via mutual information bounds between SBI and gradient-based variational inference methods that permits BOED to be used in SBI applications as SBI-BOED.
We compare this approach on SBI-based models in real-world simulators in epidemiology and biology, showing notable improvements in inference.
arXiv Detail & Related papers (2025-02-11T22:58:18Z) - Towards Autonomous Experimentation: Bayesian Optimization over Problem Formulation Space for Accelerated Alloy Development [0.31457219084519]
We introduce a novel framework that leverages Bayesian optimization over a problem formulation space to identify optimal design formulations.
We demonstrate the efficacy of our method through an in silico case study on a Mo-Nb-Ti-V-W alloy system targeted for gas turbine engine blade applications.
Future work will incorporate human feedback to further enhance the adaptability of the system in real-world experimental settings.
arXiv Detail & Related papers (2025-02-09T01:05:58Z) - Diffusion Model for Data-Driven Black-Box Optimization [54.25693582870226]
We focus on diffusion models, a powerful generative AI technology, and investigate their potential for black-box optimization.
We study two practical types of labels: 1) noisy measurements of a real-valued reward function and 2) human preference based on pairwise comparisons.
Our proposed method reformulates the design optimization problem into a conditional sampling problem, which allows us to leverage the power of diffusion models.
arXiv Detail & Related papers (2024-03-20T00:41:12Z) - Enhanced Bayesian Optimization via Preferential Modeling of Abstract
Properties [49.351577714596544]
We propose a human-AI collaborative Bayesian framework to incorporate expert preferences about unmeasured abstract properties into surrogate modeling.
We provide an efficient strategy that can also handle any incorrect/misleading expert bias in preferential judgments.
arXiv Detail & Related papers (2024-02-27T09:23:13Z) - Variational Sequential Optimal Experimental Design using Reinforcement Learning [0.0]
vsOED employs a one-point reward formulation with variational posterior approximations, providing a provable lower bound to the expected information gain.
We demonstrate vsOED across various engineering and science applications, illustrating its superior sample efficiency compared to existing sequential experimental design algorithms.
arXiv Detail & Related papers (2023-06-17T21:47:19Z) - Design Amortization for Bayesian Optimal Experimental Design [70.13948372218849]
We build off of successful variational approaches, which optimize a parameterized variational model with respect to bounds on the expected information gain (EIG)
We present a novel neural architecture that allows experimenters to optimize a single variational model that can estimate the EIG for potentially infinitely many designs.
arXiv Detail & Related papers (2022-10-07T02:12:34Z) - A Field Guide to Federated Optimization [161.3779046812383]
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data.
This paper provides recommendations and guidelines on formulating, designing, evaluating and analyzing federated optimization algorithms.
arXiv Detail & Related papers (2021-07-14T18:09:08Z) - Optimal Bayesian experimental design for subsurface flow problems [77.34726150561087]
We propose a novel approach for development of chaos expansion (PCE) surrogate model for the design utility function.
This novel technique enables the derivation of a reasonable quality response surface for the targeted objective function with a computational budget comparable to several single-point evaluations.
arXiv Detail & Related papers (2020-08-10T09:42:59Z) - Incorporating Expert Prior Knowledge into Experimental Design via
Posterior Sampling [58.56638141701966]
Experimenters can often acquire the knowledge about the location of the global optimum.
It is unknown how to incorporate the expert prior knowledge about the global optimum into Bayesian optimization.
An efficient Bayesian optimization approach has been proposed via posterior sampling on the posterior distribution of the global optimum.
arXiv Detail & Related papers (2020-02-26T01:57:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.