[Statlist] Next talk: Tuesday, 07.01.2020, with Abraham Wyner Wharton, University of Pennsylvania

[Maurer Letizia]

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

Organisers:

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

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

We are glad to announce the following talk:

Tuesday, 07.01.2020, at 11.15 h, ETH Zurich HG G19.2
with Abraham Wyner Wharton, University of Pennsylvania
*******************************************************************************


Title:

Explaining the Success of AdaBoost, Random Forests and Deep Neural Nets as Interpolating Classifiers


Abstract:

AdaBoost, random forests and deep neural networks are the present day workhorses of the machine learning universe. We introduce a novel perspective on AdaBoost and random forests that proposes that the two algorithms work for similar reasons. While both classifiers achieve similar predictive accuracy, random forests cannot be conceived as a direct optimization procedure. Rather, random forests is a self-​averaging, "interpolating" algorithm which creates what we denote as a “spiked-​smooth” classifier, and we view AdaBoost in the same light. We conjecture that both AdaBoost and random forests succeed because of this mechanism. We provide a number of examples to support this explanation. We conclude with a brief mention of new research that suggests that deep neural nets are effective (at least in part and in some contexts) for the same reasons.


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

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

Statlist mailing list
Statlist at stat.ch
https://stat.ethz.ch/mailman/listinfo/statlist



--

	[[alternative HTML version deleted]]