Learning to benchmark

Speaker: Prof. Dr. Alfred Hero
Affiliation: University of Michigan, USA
Organized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg (Germany)

Zoom meeting link
Meeting ID: TBA | PIN code: TBA

Abstract. We address the problem of learning an achievable lower bound on classification error from a labeled sample. We establish an optimization framework for this meta-learning problem, which we call benchmark learning. Benchmark learning leads to an accurate data-driven predictor of performance of a Bayes optimal classifier without having to construct the classifier and without assuming any parametric model for the data. The resultant predictor can be used to establish whether it is possible to improve classification performance of a specific classifier. It also yields a stopping rule for sequentially trained classifiers. In addition, The talk will cover relevant background, theory, algorithms, and applications of benchmark learning.

  • 00

    days

  • 00

    hours

  • 00

    minutes

  • 00

    seconds

Date

Jul 14 2021

Time

16:00 - 17:00

Location

Worldwide
FAU-DCN AvH

Organizer

FAU-DCN AvH
Website
http://www.caa-avh.nat.fau.eu
No event found!
Load More

No Responses

Leave a Reply

Your email address will not be published. Required fields are marked *

© 2019-2021 Chair for Dynamics, Control and Numerics - Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg, Germany | Imprint