To interact or not? The convergence properties of interacting stochastic mirror descent.

preview_player
Показать описание
In this video we discuss the benefits of running multiple copies of a gradient-based optimizer, which we refer to as particles, and letting these interact. This video first appeared at the ICML Workshop "Beyond first-order methods in ML systems".

Anastasia Borovykh; joint work with Panos Parpas, Nikolas Kantas and Greg Pavliotis
Рекомендации по теме
Комментарии
Автор

I want to learn optimization theory but most of the videos or channels I found have started from advanced concepts. It would be a great help for me to learn from your knowledge.

muhammadawais
Автор

Please make some videos around basic topics. Because it is hard to understand before some prior knowledge. Thank you

muhammadawais
Автор

I am totally attracted by your looks.🤨

kelvin