Learning Bounds for Risk-sensitive Learning

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 131
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorLee, Jaehoko
dc.contributor.authorPark, Sejunko
dc.contributor.authorShin, Jinwooko
dc.date.accessioned2020-12-11T06:50:34Z-
dc.date.available2020-12-11T06:50:34Z-
dc.date.created2020-12-02-
dc.date.issued2020-12-07-
dc.identifier.citation34th Conference on Neural Information Processing Systems (NeurIPS) 2020-
dc.identifier.urihttp://hdl.handle.net/10203/278228-
dc.description.abstractIn risk-sensitive learning, one aims to find a hypothesis that minimizes a risk-averse (or risk-seeking) measure of loss, instead of the standard expected loss. In this paper, we propose to study the generalization properties of risk-sensitive learning schemes whose optimand is described via optimized certainty equivalents (OCE): our general scheme can handle various known risks, e.g., the entropic risk, mean-variance, and conditional value-at-risk, as special cases. We provide two learning bounds on the performance of empirical OCE minimizer. The first result gives an OCE guarantee based on the Rademacher average of the hypothesis space, which generalizes and improves existing results on the expected loss and the conditional value-at-risk. The second result, based on a novel variance-based characterization of OCE, gives an expected loss guarantee with a suppressed dependence on the smoothness of the selected OCE. Finally, we demonstrate the practical implications of the proposed bounds via exploratory experiments on neural networks.-
dc.languageEnglish-
dc.publisherNeural Information Processing Systems-
dc.titleLearning Bounds for Risk-sensitive Learning-
dc.typeConference-
dc.type.rimsCONF-
dc.citation.publicationname34th Conference on Neural Information Processing Systems (NeurIPS) 2020-
dc.identifier.conferencecountryCN-
dc.identifier.conferencelocationVirtual-
dc.contributor.localauthorShin, Jinwoo-
dc.contributor.nonIdAuthorLee, Jaeho-
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0