#  Colloq: Alexander (Sasha) Rakhlin 

 



####  calendar\_today Date and Time 

 **January 30, 2017** 

 04:15PM - 05:15PM EST 

####  pin\_drop Location 

 **Science Center Hall E**  



 

 



 

 [An Optimal Aggregation Procedure For Nonparametric Regression](/files/statistics/files/alexander_rakhlin_-_january_30.pdf)

 How can one combine a collection of estimators of a regression function into a good aggregate? In the last 15 years, this age-old question has received increasing attention within the Mathematical Statistics community. A closely related question of regression in misspecified models has been studied within Statistical Learning using the techniques of empirical processes. We outline the shortcomings of the existing methods and present a new procedure that improves upon the least squares when the model is non-convex. We compare and contrast our estimator --- which is inspired by online methods in machine learning --- with the classical results on nonparametric regression under the assumption that the model is well-specified.

 Based on (R., Sridharan, and Tsybakov, 2014) and (Liang, R., Sridharan, 2015)



 

 



 

 See also:- [ 2016 - 2017 ](/academic-year/2016-2017)
- [ Colloquia ](/event-type/colloquia)
 
 

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


 Save: [ Add to calendar calendar\_today ](https://statistics.fas.harvard.edu/node/1122660/event-feed.ics)  Copy link link