Skip to main content

19. Dec 2024

On a geometric problem of machine learning

Algebraic Geometry and Number Theory Seminar

Datum: 19. December 2024 | 13:00 – 15:00
Sprecher: Richard Rimanyi, University of North Carolina at Chapel Hill
Veranstaltungsort: Office Bldg West / Ground floor / Heinzel Seminar Room (I21.EG.101)
Sprache: Englisch

In this talk we will enumerate the main reasons for a collection of matrices multiplying to 0. Our motivation is Bayesian Learning Theory, where one of the goals is to progressively approximate an unknown distribution using data generated from that distribution. A key component in this framework is a function K (relative entropy), which is often highly singular. The invariants of the singularities of K (in the style of log canonical threshold') are related to how well the Singular Learning Theory "generalizes"—or, in Machine Learning terms, how efficiently the model can be trained. Computing the singularity invariants in real-life scenarios of Machine Learning is notoriously difficult. In this talk, we focus on an elementary example and compute the learning coefficients of Linear Neural Networks. Joint work with S. P. Lehalleur.

Weitere Informationen:

Datum:
19. December 2024
13:00 – 15:00

Sprecher:
Richard Rimanyi, University of North Carolina at Chapel Hill

Veranstaltungsort:
Office Bldg West / Ground floor / Heinzel Seminar Room (I21.EG.101)

Sprache:
Englisch

Ansprechpartner:

Oosthuizen-Noczil Birgit

Email:
boosthui@ist.ac.at

Teilen

facebook share icon
twitter share icon



sidebar arrow up
Nach Oben