BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME;VALUE=TEXT:Colloq: Alexander (Sasha) Rakhlin
PRODID:-//Harvard events data//EN
BEGIN:VEVENT
UID:event_1122660_0
SUMMARY:Colloq: Alexander (Sasha) Rakhlin
DESCRIPTION:<p>	<a data-fid="775001" href="internal:/files/statistics/files/alexander_rakhlin_-_january_30.pdf">An Optimal Aggregation Procedure For Nonparametric Regression</a></p><p>	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.</p><p>	Based on (R., Sridharan, and Tsybakov, 2014) and (Liang, R., Sridharan, 2015)</p>
LOCATION:Science Center Hall E
STATUS:CONFIRMED
DTSTART:20170130T211500Z
DTEND:20170130T221500Z
END:VEVENT
END:VCALENDAR