Nie jesteś zalogowany |
Loss landscape of deep neural networks
- Prelegent(ci)
- Bartłomiej Polaczyk
- Termin
- 25 marca 2021 12:15
- Informacje na temat wydarzenia
- meet.google.com/yew-oubf-ngi
- Seminarium
- Seminarium "Uczenie maszynowe"
Finding the global minimum of a general non-convex function is in general an NP-complete problem. The optimization objective of deep neural networks (DNN) is not only non-convex but even non-smooth in case of ReLU activation function. Yet, practice suggests that even simple first-order methods such as gradient descent are able (in many cases) to find the global optimum of DNN at random initialization. Understanding this phenomenon is one of the core problems in theoretical machine learning.
The aim of this talk is to give literature overview of the above subject, presenting historical background, recent important contributions and discussing some still open problems.
