Functional norm regularization for margin-based ranking on temporal data

Abstract

Quantifying the properties of interest is an important problem in many domains, e.g., assessing the condition of a patient, estimating the risk of an investment or relevance of the search result. However, the properties of interest are often latent and hard to assess directly, making it dicult to obtain classication or regression labels, which are needed to learn a predictive models from observable features. In such cases, it is typically much easier to obtain relative comparison of two instances, i.e. to assess which one is more intense (with respect to the property of interest). One framework able to learn from such kind of supervised information is ranking SVM, and it will make a basis of our approach...

Kvantikovanje osobina (karakteristika) od interesa je vazan problem u mnogim domenima, npr. utvrdivanje tezine bolesti kod pacijenata, ocena rizika investicije ili relevantnost vracenih rezultata pretrage. Medutim, osobine od interesa su cesto latentne i tesko se mogu izmeriti direktno, sto otezava dobijanje klasikacionih oznaka (labela) ili ciljeva za regresiju, koji su potrebni za ucenje prediktivnih modela iz merljivih karakteristika. U takvim slucajevima obicno je mnogo lakse pribaviti relativno poredenje dva slucaja, tj. proceniti koji od dva je intenzivniji (iz ugla karakteristike od interesa). Jedna klasa algoritama koji mogu uciti iz ovakvih informacija je SVM za rangiranje i on ce biti osnova ovde predlozenog pristupa...