search

UMD     This Site





Approximate Bayesian inference is a statistical learning methodology with wide-ranging applications in sequential information collection problems, particularly those where a decision maker must use incomplete or censored information to maintain and update a set of beliefs about one or more unknown population parameters. Approximate Bayesian models are attractive for their computational tractability and often lead to compact belief representations that can interface with simple and interpretable policies for related decision problems.

Approximate Bayesian methods have repeatedly demonstrated significant practical benefits. They have been successfully used for market design, posted price auctions, online gaming, big-data analytics, approximate dynamic programming and ranking and selection.

However, virtually all of the existing work on sequential approximate Bayesian learning is computational/algorithmic in nature, and the consistency of approximate Bayesian estimators has been a largely open problem, mostly unamenable to the usual forms of consistency analysis.

A new paper in the journal Operations Research, Consistency Analysis of Sequential Learning Under Approximate Bayesian Inference, develops a theoretical framework that can be leveraged to produce new consistency proofs.

Associate Professor Ilya Ryzhov (BMG/ISR) and his former student Ye Chen (Math Ph.D. 2018) introduce a new consistency theory that interprets approximate Bayesian inference as a form of stochastic approximation (SA) with an additional “bias” term. They prove the convergence of a general SA algorithm of this form and leverage this analysis to derive the first consistency proofs for a suite of approximate Bayesian models from the recent literature.

This paper is among the first to provide broad theoretical support for approximate Bayesian procedures. The authors prove, for the first time, the statistical consistency of a wide variety of previously proposed approximate Bayesian estimators, providing insight into their good empirical performance. They also develop theoretical tools that may be used by researchers to develop similar proofs for other problems and applications.



Related Articles:
Neural and computational mechanisms underlying musical enculturation
When does a package delivery company benefit from having two people in the truck?
Al-Obaid, Adomaitis publish renewable energy algorithm in Royal Society of Chemistry journal
S. Raghu Raghavan is a runner-up for INFORMS Computing Society Prize
Michael Fu part of $1M NSF grant to model, disrupt illicit kidney trafficking networks
Alexander Estes joins ISR faculty
Alum Marcos Vasconcelos to join FSU faculty this fall
In Memoriam: 'Advisor for Life' Pravin Varaiya
Fatemeh Alimardani receives WTS-DC scholarship
Michael Fu part of NSF project to improve kidney transplant access and decision-making

January 7, 2020


«Previous Story  

 

 

Current Headlines

Srivastava Named Inaugural Director of Semiconductor Initiatives and Innovation

State-of-the-Art 3D Nanoprinter Now at UMD

UMD, Partners Receive $31M for Semiconductor Research

Two NSF Awards for ECE Alum Michael Zuzak (Ph.D. ’22)

Applications Open for Professor and Chair of UMD's Department of Materials Science and Engineering

Ghodssi Honored With Gaede-Langmuir Award

Milchberg and Wu named Distinguished University Professors

New features on ingestible capsule will deliver targeted drugs to better treat IBD, Crohn’s disease

Forty years of MEMS research at the Hilton Head Workshop

Baturalp Buyukates (ECE Ph.D. ’21) Honored by IEEE ComSoc

 
 
Back to top  
Home Clark School Home UMD Home