SRM-based Service Discovery Method in Information System Architecture Design

Zhang, Xiaoxue; Chen, Tao; Xu, Chentao; Zhang, Zhaochen

doi:10.1109/icaice54393.2021.00141

Cited by 2 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent advancements have introduced efficient gradientbased approaches that leverage the reparameterization trick and automatic differentiation frameworks. These methods, such as those proposed in (Foster et al 2020;Kleinegesse and Gutmann 2020;Zhang, Bi, and Zhang 2021;Zaballa and Hui 2023), allow for simultaneous optimization of both the variational parameters and the design variables. Moreover, Goda et al (Goda et al 2022) presented a method that directly obtains an unbiased estimator of the EIG gradient using a randomized version of multilevel Monte Carlo (MLMC) method (Rhee and Glynn 2015).…”

Section: Related Workmentioning

confidence: 99%

On Estimating the Gradient of the Expected Information Gain in Bayesian Experimental Design

Ao,

2024

AAAI

View full text Add to dashboard Cite

Bayesian Experimental Design (BED), which aims to find the optimal experimental conditions for Bayesian inference, is usually posed as to optimize the expected information gain (EIG). The gradient information is often needed for efficient EIG optimization, and as a result the ability to estimate the gradient of EIG is essential for BED problems. The primary goal of this work is to develop methods for estimating the gradient of EIG, which, combined with the stochastic gradient descent algorithms, result in efficient optimization of EIG. Specifically, we first introduce a posterior expected representation of the EIG gradient with respect to the design variables. Based on this, we propose two methods for estimating the EIG gradient, UEEG-MCMC that leverages posterior samples generated through Markov Chain Monte Carlo (MCMC) to estimate the EIG gradient, and BEEG-AP that focuses on achieving high simulation efficiency by repeatedly using parameter samples. Theoretical analysis and numerical studies illustrate that UEEG-MCMC is robust agains the actual EIG value, while BEEG-AP is more efficient when the EIG value to be optimized is small. Moreover, both methods show superior performance compared to several popular benchmarks in our numerical experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

On Estimating the Gradient of the Expected Information Gain in Bayesian Experimental Design

Ao,

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…It is also useful for evaluation, as it can be used in conjunction with (8) to provide upper and lower limits on the true EIG. Variations on this unified variational SGA approach to BED have since been developed by [32,61,76,148].…”

Section: Optimizationmentioning

confidence: 99%

“…An inevitable problem with all these gradient-based approaches occurs when the design space or likelihood function is not continuous, for example because some design decisions are discrete. Relaxation schemes can, in principle, allow such cases to be dealt with [62,148], but further work is still required to fully address this problem.…”

Section: Optimizationmentioning

confidence: 99%

Modern Bayesian Experimental Design

Rainforth¹,

Foster²,

Ivanova³

et al. 2023

Preprint

View full text Add to dashboard Cite

Bayesian experimental design (BED) provides a powerful and general framework for optimizing the design of experiments. However, its deployment often poses substantial computational challenges that can undermine its practical use. In this review, we outline how recent advances have transformed our ability to overcome these challenges and thus utilize BED effectively, before discussing some key areas for future development in the field.

show abstract

SRM-based Service Discovery Method in Information System Architecture Design

Cited by 2 publications

References 3 publications

On Estimating the Gradient of the Expected Information Gain in Bayesian Experimental Design

On Estimating the Gradient of the Expected Information Gain in Bayesian Experimental Design

Modern Bayesian Experimental Design

Contact Info

Product

Resources

About