For several machine learning methods such as neural networks, good generalisation performance has been reported in the overparametrized regime. In view of the classical bias-variance trade-off, this behaviour is highly counterintuitive. The talk summarizes recent theoretical results on overparametrization and the bias-variance trade-off. This is joint work with Alexis Derumigny.
Underlying paper: https://arxiv.org/pdf/2006.00278.pdf
Personal website of Johannes Schmidt-Hieber
The talk also can be joined online via our ZOOM MEETING
Meeting room opens at: April 04, 2022, 4.30 pm Vienna
Meeting ID: 619 4329 4932
Password: 961880