Scientific Calendar Event



Starts 8 Jun 2021 15:00
Ends 8 Jun 2021 16:00
Central European Time
Zoom Meeting
Join Zoom Meeting https://zoom.us/j/475819702
Meeting ID: 475-819-702

If you haven't registered for previous QLS webinars, please contact qls@ictp.it to obtain the PASSWORD for this zoom meeting.

The past decade has witnessed a surge in the development and adoption of machine learning algorithms to solve day-a-day computational tasks. Yet, a solid theoretical understanding of even the most basic tools used in practice is still lacking. Surprisingly, many of the “exotic” behaviours of deep neural networks have shown to hold in models as simple as high-dimensional linear regression. In this talk, I will introduce two simple toy models describing learning with correlated features. Next, I will motivate how these models encompass many learning problems of interest, e.g. ridge and logistic regression, kernel methods, random features, scattering transforms and transfer learning. Finally, I will discuss how these models can be used to approximate real data learning curves in some scenarios.