[Statlist] Next talk: Friday, 11.10.2019, with Ashia Wilson, Microsoft Research

Maurer Letizia |et|z|@m@urer @end|ng |rom ethz@ch
Fri Oct 4 11:05:49 CEST 2019


E-mail from the  Statlist using stat.ch<mailto:Statlist using stat.ch>  mailing list
_______________________________________________
ETH and University of Zurich

Organisers:

Proff. P. Bühlmann - L. Held - T. Hothorn - M. Maathuis -
N. Meinshausen - S. van de Geer - M. Wolf

****************************************************************************

We are glad to announce the following talk:

Friday, 11.10.2019, at 15.15 h  ETH Zurich HG G19.1
with Ashia Wilson, Microsoft Research

*****************************************************************************


Title:

The risk of approximate cross validation <https://math.ethz.ch/sfs/news-and-events/research-seminar.html?s=hs19#e_14206>


Abstract:

Cross-validation (CV) is the de facto standard for selecting accurate predictive models and assessing model performance. However, CV suffers from a need to repeatedly refit a learning procedure on a large number of training datasets. To reduce the computational burden, a number of works have introduced approximate CV procedures that simultaneously reduce runtime and provide model assessments comparable to CV when the prediction problem is sufficiently smooth. An open question however is whether these procedures are suitable for model selection. In this talk, I’ll describe (i) broad conditions under which the model selection performance of approximate CV nearly matches that of CV, (ii) examples of prediction problems where approximate CV selection fails to mimic CV selection, and (iii) an extension of these results and the approximate CV framework more broadly to non-smooth prediction problems like L1-regularized empirical risk minimization. This is joint work with Lester Mackey and Maximilian Kasy.


This abstract is also to be found under the following link: http://stat.ethz.ch/events/research_seminar

*******************************************************************************************************************

Statlist mailing list
Statlist using stat.ch<mailto:Statlist using stat.ch>
https://stat.ethz.ch/mailman/listinfo/statlist


--
ETH Zürich
Letizia Maurer
Administration
Departement Mathematik
HG J 64
Rämistrasse 101
8092 Zürich

Telefon +41 44 632 3396
cletizia using ethz.ch<mailto:cletizia using ethz.ch>




	[[alternative HTML version deleted]]



More information about the Statlist mailing list