BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Recent Developments in Linear Regression
DTSTART:20171212T161500
DTSTAMP:20260406T184702Z
UID:feb8375b80e062b04d61ce8286f1bae7762c58998197c711a784f76a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Martin Jaeggi (EPFL\, IC\, INFCOM\, MLO)\nWe will overvi
 ew some recent advances in optimization algorithms used for the training o
 f generalized linear models (regression\, classification). While in machin
 e learning\, the main work-horse algorithm is stochastic gradient descent\
 , its lesser known cousin\, coordinate descent\, also has a lot of interes
 ting properties. After a brief introduction\, we will discuss distributed 
 algorithm variants as well as faster convergence by means of (constant or 
 adaptive) importance sampling.
LOCATION:GR A3 32 https://plan.epfl.ch/?room==GR%20A3%2032
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR