Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287327368> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4287327368 abstract "Given a prediction task, understanding when one can and cannot design a consistent convex surrogate loss, particularly a low-dimensional one, is an important and active area of machine learning research. The prediction task may be given as a target loss, as in classification and structured prediction, or simply as a (conditional) statistic of the data, as in risk measure estimation. These two scenarios typically involve different techniques for designing and analyzing surrogate losses. We unify these settings using tools from property elicitation, and give a general lower bound on prediction dimension. Our lower bound tightens existing results in the case of discrete predictions, showing that previous calibration-based bounds can largely be recovered via property elicitation. For continuous estimation, our lower bound resolves on open problem on estimating measures of risk and uncertainty." @default.
- W4287327368 created "2022-07-25" @default.
- W4287327368 creator A5009598002 @default.
- W4287327368 creator A5076830609 @default.
- W4287327368 creator A5077451185 @default.
- W4287327368 date "2021-02-16" @default.
- W4287327368 modified "2023-09-28" @default.
- W4287327368 title "Unifying Lower Bounds on Prediction Dimension of Consistent Convex Surrogates" @default.
- W4287327368 hasPublicationYear "2021" @default.
- W4287327368 type Work @default.
- W4287327368 citedByCount "0" @default.
- W4287327368 crossrefType "posted-content" @default.
- W4287327368 hasAuthorship W4287327368A5009598002 @default.
- W4287327368 hasAuthorship W4287327368A5076830609 @default.
- W4287327368 hasAuthorship W4287327368A5077451185 @default.
- W4287327368 hasBestOaLocation W42873273681 @default.
- W4287327368 hasConcept C105795698 @default.
- W4287327368 hasConcept C111472728 @default.
- W4287327368 hasConcept C112680207 @default.
- W4287327368 hasConcept C11413529 @default.
- W4287327368 hasConcept C114614502 @default.
- W4287327368 hasConcept C119322782 @default.
- W4287327368 hasConcept C119857082 @default.
- W4287327368 hasConcept C124101348 @default.
- W4287327368 hasConcept C126255220 @default.
- W4287327368 hasConcept C134306372 @default.
- W4287327368 hasConcept C138885662 @default.
- W4287327368 hasConcept C154945302 @default.
- W4287327368 hasConcept C162324750 @default.
- W4287327368 hasConcept C165838908 @default.
- W4287327368 hasConcept C187736073 @default.
- W4287327368 hasConcept C189950617 @default.
- W4287327368 hasConcept C2524010 @default.
- W4287327368 hasConcept C2780009758 @default.
- W4287327368 hasConcept C2780451532 @default.
- W4287327368 hasConcept C33676613 @default.
- W4287327368 hasConcept C33923547 @default.
- W4287327368 hasConcept C41008148 @default.
- W4287327368 hasConcept C77553402 @default.
- W4287327368 hasConcept C89128539 @default.
- W4287327368 hasConceptScore W4287327368C105795698 @default.
- W4287327368 hasConceptScore W4287327368C111472728 @default.
- W4287327368 hasConceptScore W4287327368C112680207 @default.
- W4287327368 hasConceptScore W4287327368C11413529 @default.
- W4287327368 hasConceptScore W4287327368C114614502 @default.
- W4287327368 hasConceptScore W4287327368C119322782 @default.
- W4287327368 hasConceptScore W4287327368C119857082 @default.
- W4287327368 hasConceptScore W4287327368C124101348 @default.
- W4287327368 hasConceptScore W4287327368C126255220 @default.
- W4287327368 hasConceptScore W4287327368C134306372 @default.
- W4287327368 hasConceptScore W4287327368C138885662 @default.
- W4287327368 hasConceptScore W4287327368C154945302 @default.
- W4287327368 hasConceptScore W4287327368C162324750 @default.
- W4287327368 hasConceptScore W4287327368C165838908 @default.
- W4287327368 hasConceptScore W4287327368C187736073 @default.
- W4287327368 hasConceptScore W4287327368C189950617 @default.
- W4287327368 hasConceptScore W4287327368C2524010 @default.
- W4287327368 hasConceptScore W4287327368C2780009758 @default.
- W4287327368 hasConceptScore W4287327368C2780451532 @default.
- W4287327368 hasConceptScore W4287327368C33676613 @default.
- W4287327368 hasConceptScore W4287327368C33923547 @default.
- W4287327368 hasConceptScore W4287327368C41008148 @default.
- W4287327368 hasConceptScore W4287327368C77553402 @default.
- W4287327368 hasConceptScore W4287327368C89128539 @default.
- W4287327368 hasLocation W42873273681 @default.
- W4287327368 hasOpenAccess W4287327368 @default.
- W4287327368 hasPrimaryLocation W42873273681 @default.
- W4287327368 hasRelatedWork W11562254 @default.
- W4287327368 hasRelatedWork W12246666 @default.
- W4287327368 hasRelatedWork W1279312 @default.
- W4287327368 hasRelatedWork W2285574 @default.
- W4287327368 hasRelatedWork W2792870 @default.
- W4287327368 hasRelatedWork W2804300 @default.
- W4287327368 hasRelatedWork W3335761 @default.
- W4287327368 hasRelatedWork W3422034 @default.
- W4287327368 hasRelatedWork W7699138 @default.
- W4287327368 hasRelatedWork W9035903 @default.
- W4287327368 isParatext "false" @default.
- W4287327368 isRetracted "false" @default.
- W4287327368 workType "article" @default.