#  Probabilitas Seminar Series: Murat Erdogdu 

 



####  calendar\_today Date and Time 

 **February 23, 2024** 

 10:30AM - 11:30AM EST 

####  pin\_drop Location 

 **Science Center 316**  



 

 



 

 The Probabilitas Seminar series focuses on high-dimensional problems that combine statistics, probability, information theory, computer science, and other related fields. The upcoming seminar takes place on Friday, February 23, from 10:30-11:30am EST. This week's guest will be Murat Erdogdu of the Univesity of Toronto.

 Title: Feature Learning in Two-layer Neural Networks: The Effect of Data Covariance  
  
Abstract: We study the effect of gradient-based optimization on  
feature learning in two-layer neural networks. We consider a setting  
where the number of samples is of the same order as the input  
dimension and show that, when the input data is isotropic, gradient  
descent always improves upon the initial random features model in  
terms of prediction risk, for a certain class of targets. Further  
leveraging the practical observation that data often contains  
additional structure, i.e., the input covariance has non-trivial  
alignment with the target, we prove that the class of learnable  
targets can be significantly extended, demonstrating a clear  
separation between kernel methods and two-layer neural networks in  
this regime.



 

 



 

 

 Share on:- [     Facebook ](#)
- [     Twitter ](#)
- [     Linkedin ](#)
 


 Save: [ Add to calendar calendar\_today ](https://statistics.fas.harvard.edu/node/1562141/event-feed.ics)  Copy link link