Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/98580
PIRA download icon_1.1View/Download Full Text
Title: Calculating optimistic likelihoods using (geodesically) convex optimization
Authors: Nguyen, VA
Shafieezadeh-Abadeh, S
Yue, MC 
Kuhn, D
Wiesemann, W
Issue Date: 2019
Source: Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019, v. 18 13875-13886
Abstract: A fundamental problem arising in many areas of machine learning is the evaluation of the likelihood of a given observation under different nominal distributions. Frequently, these nominal distributions are themselves estimated from data, which makes them susceptible to estimation errors. We thus propose to replace each nominal distribution with an ambiguity set containing all distributions in its vicinity and to evaluate an optimistic likelihood, that is, the maximum of the likelihood over all distributions in the ambiguity set. When the proximity of distributions is quantified by the Fisher-Rao distance or the Kullback-Leibler divergence, the emerging optimistic likelihoods can be computed efficiently using either geodesic or standard convex optimization techniques. We showcase the advantages of working with optimistic likelihoods on a classification problem using synthetic as well as empirical data.
Publisher: NeurIPS
ISBN: 978-1-7138-0793-3 (Print on Demand(PoD))
Description: 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), 8-14 Dec 2019, Vancouver, Canada
Rights: Copyright© (2019) by individual authors and Neural Information Processing Systems Foundation Inc.
Posted with permission of the author.
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
Nguyag_Calculating_Optimistic_Likelihoods.pdf564.65 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

41
Citations as of Mar 24, 2024

Downloads

11
Citations as of Mar 24, 2024

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.