Sparse Online Learning via Truncated Gradient

Simple item page
dc.creatorLangford, John
dc.creatorLi, Lihong
dc.creatorZhang, Tong
dc.date2008-06-28
dc.date2008-07-04
dc.date.accessioned2026-07-07T09:48:11Z
dc.date.available2026-07-07T09:48:11Z
dc.descriptionWe propose a general method called truncated gradient to induce sparsity in the weights of online learning algorithms with convex loss functions. This method has several essential properties: The degree of sparsity is continuous -- a parameter controls the rate of sparsification from no sparsification to total sparsification. The approach is theoretically motivated, and an instance of it can be regarded as an online counterpart of the popular $L_1$-regularization method in the batch setting. We prove that small rates of sparsification result in only small additional regret with respect to typical online learning guarantees. The approach works well empirically. We apply the approach to several datasets and find that for datasets with large numbers of features, substantial sparsity is discoverable.
dc.identifierhttps://arxiv.org/abs/0806.4686
dc.identifierhttp://arxiv.org/abs/0806.4686
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/164117
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.titleSparse Online Learning via Truncated Gradient
dc.typetext

Files

Collections

arXiv