[Statlist] Next talk: Monday, 03.09.2018, with Ludwig Schmidt, University of California, Berkeley

[Maurer Letizia]

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:

Monday, 03.09.2018, at 15.00h  ETH Zurich HG G19.1
with Ludwig Schmidt, University of California, Berkeley

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


Title:

How robust is current machine learning? A perspective on overfitting and (adversarial) distribution shifts

Abstract:

Machine learning is now being deployed in safety- and security-critical systems such as autonomous vehicles, medical devices, and large recommender systems. If we want to use machine learning in these scenarios responsibly, we need to understand how reliable our current methodology is. One potential danger in the common ML workflow is the repeated use of the same test set for parameter tuning. To investigate this issue, I will present results of a reproducibility study on the popular CIFAR-10 dataset. Surprisingly, we find no signs of overfitting despite multiple years of adaptive classifier tuning. Nevertheless, our results show that current classifiers are already susceptible to benign shifts in distribution.

In the second part of the talk, I will then describe how robust optimization can address some of the challenges arising from distribution shifts in the form of adversarial examples. By exploring the loss landscape of min-max problems in deep neural networks, we can train classifiers with state-of-the art robustness to l_infinity perturbations and small spatial transformations.

Based on joint works with Logan Engstrom, Aleksander Madry, Aleksandar Makelov, Benjamin Recht, Rebecca Roelofs, Vaishaal Shankar, Brandon Tran, Dimitris Tsipras, and Adrian Vladu.

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

	[[alternative HTML version deleted]]