Efficient Algorithm for Regularized Risk Minimization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00200337" target="_blank" >RIV/68407700:21230/12:00200337 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Algorithm for Regularized Risk Minimization

Popis výsledku v původním jazyce

Many machine learning algorithms lead to solving a convex regularized risk minimization problem. Despite its convexity the problem is often very demanding in practice due to a high number of variables or a complex objective function. The Bundle Method for Risk Minimization (BMRM) is a recently proposed method for minimizing a generic regularized risk. Unlike the approximative methods, the BMRM algorithm comes with convergence guarantees but it is often too slow in practice. We propose a modified variantof the BMRM algorithm which decomposes the objective function into several parts and approximates each part by a separate cutting plane model instead of a single cutting plane model used in the original BMRM. The finer approximation of the objective function can significantly decrease the number of iterations at the expense of higher memory requirements. A preliminary experimental comparison shows promising results.

Název v anglickém jazyce

Efficient Algorithm for Regularized Risk Minimization

Popis výsledku anglicky

Many machine learning algorithms lead to solving a convex regularized risk minimization problem. Despite its convexity the problem is often very demanding in practice due to a high number of variables or a complex objective function. The Bundle Method for Risk Minimization (BMRM) is a recently proposed method for minimizing a generic regularized risk. Unlike the approximative methods, the BMRM algorithm comes with convergence guarantees but it is often too slow in practice. We propose a modified variantof the BMRM algorithm which decomposes the objective function into several parts and approximates each part by a separate cutting plane model instead of a single cutting plane model used in the original BMRM. The finer approximation of the objective function can significantly decrease the number of iterations at the expense of higher memory requirements. A preliminary experimental comparison shows promising results.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/7E10047" target="_blank" >7E10047: Humanoids with auditory and visual abilities in populated spaces</a><br>

Návaznosti

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

Rok uplatnění

2012

Kód důvěrnosti údajů

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

Název statě ve sborníku

CVWW 2012: Proceedings of the 17th Computer Vision Winter Workshop

ISBN

978-961-90901-6-9

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

57-64

Název nakladatele

Slovenian Pattern Recognition Society

Místo vydání

Ljubljana

Místo konání akce

Mala Nedelja

Datum konání akce

1. 2. 2012

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—