Learning with incremental iterative regularization

TitleLearning with incremental iterative regularization
Publication TypeConference Paper
Year of Publication2015
AuthorsRosasco, L, Villa, S
Conference NameNIPS 2015
Other Numbersarxiv:1405.0042

Within a statistical learning setting, we propose and study an iterative regularization algorithm for least squares defined by an incremental gradient method. In particular, we show that, if all other parameters are fixed a priori, the number of passes over the data (epochs) acts as a regularization parameter, and prove strong universal consistency, i.e. almost sure convergence of the risk, as well as sharp finite sample bounds for the iterates. Our results are a step towards understanding the effect of multiple epochs in stochastic gradient techniques in machine learning and rely on integrating statistical and optimizationresults.


Research Area: 

CBMM Relationship: 

  • CBMM Related