We use a few cookies

Essential cookies keep the library working. With your permission, we'd also like to use analytics to see what's useful and improve the experience. Read our Privacy Policy or Cookie Policy.

Skip to main content
Home/e-Resources/Computer Science & Information Technology/On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions
PeriodicalsComputer Science & Information Technology

On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions

arXiv2013

Checking your access to this record.

Abstract & Overview

In this paper, we study the generalization properties of online learning based stochastic methods for supervised learning problems where the loss function is dependent on more than one training sample (e.g., metric learning, ranking). We present a generic decoupling technique that enables us to provide Rademacher complexity-based generalization error bounds. Our bounds are in general tighter than those obtained by Wang et al (COLT 2012) for the same problem. Using our decoupling technique, we are further able to obtain fast convergence rates for strongly convex pairwise loss functions. We are also able to analyze a class of memory efficient online learning algorithms for pairwise learning problems that use only a bounded subset of past training samples to update the hypothesis at each step. Finally, in order to complement our generalization bounds, we propose a novel memory efficient online learning algorithm for higher order learning problems with bounded regret guarantees.

Cite this record

Purushottam Kar, Bharath K Sriperumbudur, Prateek Jain, Harish C Karnick (2013). On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions. arXiv. https://library.shubhaarti.com/content/8586f122-5fee-4141-bc13-8e8e469f18fd

Copy in another style

Kar, P., Sriperumbudur, B. K., Jain, P., & Karnick, H. C. (2013). On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions. arXiv. https://library.shubhaarti.com/content/8586f122-5fee-4141-bc13-8e8e469f18fd
Author names are used as deposited, so check their order before you submit.

Metadata is harvested from open-access indexes and can be incomplete. Check a citation against the published version before relying on it — see our open access & attribution policy.