- Lecturer: Nihat Ay
- Date: Thursday 15:15 - 16:45
- Room: Videobroadcast
- Prerequisites: Linear algebra, elementary probability theory, basic notions from functional analysis
- Remarks: Please register with Nihat Ay by November 15.
AbstractStatistical learning theory (SLT) is a powerful framework to study the generalisation ability of learning machines (their performance in the context of new data). The corresponding bounds depend on certain capacity measures that quantify the expressivity of the underlying architecture (how many different functions it can represent). Recent case studies have shown that the high performance of state-of-the-art learning machines, particularly deep neural networks, cannot be explained within the framework of classical SLT. On the one hand, such systems work extremely well in over-parametrised regimes where the classical bounds, being strongly dependent on the number of parameters, become uninformative. On the other hand, some evidence suggests that convergence and generalisation should be controlled by bounds that depend on some norm of the optimal solution, rather than the capacity of the architecture. The control of this norm is believed to be strongly dependent on the optimisation algorithm at hand.
See a outline of the seminar, together with some key references.
The seminar has been prepared in collaboration with Juan Pablo Vigneaux.
- Introduction to Enumerative Geometry
- Fulvio Gesmundo
- January 11 / 13 / 15 / 18 / 20 / 22, 2021: 16:30 - 18:30 CET, Videobroadcast
- Riemann Surfaces and Algebraic Curves
- Daniele Agostini, Rainer Sinn
- Wednesday 15:15 - 16:45 (lectures), Wednesday 11:00 - 12:30 (exercise sessions)
- The course will take place on Zoom. Please send an email to Daniele Agostini for the link.
- Kernel Methods in Learning Theory (Course)
- Nihat Ay
- Thursday 11:15 - 12:45, first meeting on November 19. , Videobroadcast
- Recent Developments Towards a New Theory of Generalisation (Seminar)
- Nihat Ay
- Thursday 15:15 - 16:45, Videobroadcast
- Selected topics in large deviations theory
- Benjamin Gess
- Friday, 16:15-17:45, Videobroadcast
- IMPRS Ringvorlesung
- Noémie Combe, Jonas Hirsch, Jürgen Jost
- 13.30 - 15.00, see schedule for dates, Videobroadcast