[Statlist] Next talk: Friday, November 9, 2012, with Garvesh Raskutti, University of California, Berkeley, USA

[Cecilia Rey]

ETH and University of Zurich

Proff. P. Buehlmann -  L. Held - H.R. Kuensch -
M. Maathuis -  S. van de Geer - M. Wolf


***********************************************************
We are glad to announce the following talk
Fridayy, November 9, 2012, 15.15h, HG G 19.1

**********************************************************
by Garvesh Raskutti, University of California, Berkeley, USA

Titel:
Early stopping of gradient descent for non-parametric regression: An optimal data-dependent stopping rule


Abstract
The phenomenon of overfitting is ubiquitous throughout statistics, and is particularly problematic in non-parametric problems. As a result,  regularization or shrinkage estimators are used. The early stopping strategy is to run an iterative algorithm for a fixed but finite number  of iterations. Early stopping of iterative algorithms is known to achieve regularization since it implicitly shrinks the solution of the un-regularized objective towards the starting point of the algorithm. When using early stopping as a strategy for regularization,a critical issue is determining when to stop. In this talk, I present analysis for an iterative update corresponding to gradient descent applied to the  non-parametric least-squares loss in an appropriately chosen co-ordinate system. In particular, for our iterative update, I present a computable data-dependent stopping rule developed by me and my former advisors. Our stopping rule achieves minimax optimal rates in mean-squared error for Sobolev space or finite-rank Reproducing kernel Hilbert space (RKHS). Importantly, our stopping rule does not require data-intensive methods such as cross-validation or hold-out data and has optimal mean-squared error performance. 

This work is joint with my former advisors, Martin Wainwright and Bin Yu.


The abstract is also to be found here:  http://stat.ethz.ch/events/research_seminar

_______________________________________________
Statlist mailing list
Statlist using stat.ch
https://stat.ethz.ch/mailman/listinfo/statlist
==========================================================================