Non-smooth non-convex optimization for training deep neural networks

Course guarantor:

Jakub Mareček

Lecturer:

Allen Robert Gehret, Jakub Mareček

Tutor:

Adam Bosák, Allen Robert Gehret, Andrii Kliachkin, Jakub Mareček

Supervisor:

Department of Computer Science

Synopsis:

Requirements:

Syllabus of lectures:

Syllabus of tutorials:

Study Objective:

Study materials:

Allen Gehret et al., Deep Learning as the Disciplined Construction of Tame Objects, https://arxiv.org/abs/2509.18025

Lou van den Dries, Tame topology and o-minimal structures, London Mathematical Society Lecture Note Series, vol. 248, Cambridge University Press, Cambridge, 1998.

Damek Davis, Dmitriy Drusvyatskiy, Sham Kakade, and Jason D Lee, Stochastic subgradient method converges on tame functions, Foundations of computational mathematics 20 (2020), no. 1, 119154.

A. D. Ioffe, An invitation to tame optimization, SIAM Journal on Optimization 19 (2008), no. 4, 18941917.

Note:

Time-table for winter semester 2025/2026:

Time-table is not available yet

Time-table for summer semester 2025/2026:

	06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon	roomKN:A-427 Mareček J. Gehret A. 11:00–12:30 (lecture parallel1) Karlovo nám. roomKN:A-427 Kliachkin A. Bosák A. 12:45–14:15 (lecture parallel1 parallel nr.101) Karlovo nám.
Tue
Wed
Thu
Fri

The course is a part of the following study plans: