Variational Bayesian Decision-making for Continuous Utilities release_i3rhneiwfbbatfkjkkzpp4ng7y

by Tomasz Kuśmierczyk, Joseph Sakaya, Arto Klami

Released as a article .

2019  

Abstract

Bayesian decision theory outlines a rigorous framework for making optimal decisions based on maximizing expected utility over a model posterior. However, practitioners often do not have access to the full posterior and resort to approximate inference strategies. In such cases, taking the eventual decision-making task into account while performing the inference allows for calibrating the posterior approximation to maximize the utility. We present an automatic pipeline that co-opts continuous utilities into variational inference algorithms to account for decision-making. We provide practical strategies for approximating and maximizing the gain, and empirically demonstrate consistent improvement when calibrating approximations for specific utilities.
In text/plain format

Archived Files and Locations

application/pdf  1.1 MB
file_mjou3so74fh6reblx62z2rxjhu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-10-27
Version   v3
Language   en ?
arXiv  1902.00792v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: bca2c1ea-2bc4-4000-a810-f862ee5ac535
API URL: JSON