Consistency of structured output learning with missing labels

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00240179" target="_blank" >RIV/68407700:21230/15:00240179 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Consistency of structured output learning with missing labels
Original language description
In this paper we study statistical consistency of partial losses suitable for learning structured output predictors from examples containing missing labels. We provide sufficient conditions on data generating distribution which admit to prove that the expected risk of the structured predictor learned by minimizing the partial loss converges to the optimal Bayes risk defined by an associated complete loss. We define a concept of surrogate classification calibrated partial losses which are easier to optimize yet their minimization preserves the statistical consistency. We give some concrete examples of surrogate partial losses which are classification calibrated. In particular, we show that the ramp-loss which is in the core of many existing algorithms is classification calibrated.
Czech name
—
Czech description
—

Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 7th Asian Conference on Machine Learning
ISBN
—
ISSN
1532-4435
e-ISSN
—
Number of pages
15
Pages from-to
81-95
Publisher name
Microtome Publishing
Place of publication
Brookline
Event location
Hong Kong
Event date
Nov 20, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)