V-shaped interval insensitive loss for ordinal classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00243387" target="_blank" >RIV/68407700:21230/16:00243387 - isvavai.cz</a>

Výsledek na webu

<a href="http://cmp.felk.cvut.cz/pub/cmp/articles/franc/Antoniuk-VILMA-ML2016-submission.pdf" target="_blank" >http://cmp.felk.cvut.cz/pub/cmp/articles/franc/Antoniuk-VILMA-ML2016-submission.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10994-015-5541-9" target="_blank" >10.1007/s10994-015-5541-9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

V-shaped interval insensitive loss for ordinal classification

Popis výsledku v původním jazyce

We address a problem of learning ordinal classifiers from partially annotated examples. We introduce a V-shaped interval-insensitive loss function to measure discrepancy between predictions of an ordinal classifier and a partial annotation provided in the form of intervals of candidate labels. We show that under reasonable assumptions on the annotation process the Bayes risk of the ordinal classifier can be bounded by the expectation of an associated interval-insensitive loss. We propose several convex surrogates of the interval-insensitive loss which are used to formulate convex learning problems. We described a variant of the cutting plane method which can solve large instances of the learning problems. Experiments on a real-life application of human age estimation show that the ordinal classifier learned from cheap partially annotated examples can achieve accuracy matching the results of the so-far used supervised methods which require expensive precisely annotated examples.

Název v anglickém jazyce

V-shaped interval insensitive loss for ordinal classification

Popis výsledku anglicky

We address a problem of learning ordinal classifiers from partially annotated examples. We introduce a V-shaped interval-insensitive loss function to measure discrepancy between predictions of an ordinal classifier and a partial annotation provided in the form of intervals of candidate labels. We show that under reasonable assumptions on the annotation process the Bayes risk of the ordinal classifier can be bounded by the expectation of an associated interval-insensitive loss. We propose several convex surrogates of the interval-insensitive loss which are used to formulate convex learning problems. We described a variant of the cutting plane method which can solve large instances of the learning problems. Experiments on a real-life application of human age estimation show that the ordinal classifier learned from cheap partially annotated examples can achieve accuracy matching the results of the so-far used supervised methods which require expensive precisely annotated examples.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Machine Learning

ISSN

0885-6125

e-ISSN

—

Svazek periodika

103

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

23

Strana od-do

261-283

Kód UT WoS článku

000374683800006

EID výsledku v databázi Scopus

2-s2.0-84953378956