BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Robust Estimation via Robust Gradient Estimation
DTSTART:20180622T110000
DTEND:20180622T120000
DTSTAMP:20260408T233617Z
UID:40d68ae3ba4f35158f407fc94eeeaad44706be7f55686fd7b7481eae
CATEGORIES:Conferences - Seminars
DESCRIPTION:Pradeep Ravikumar\,  Professor at School of Computer Science\
 , Carnegie Mellon University\nProf. Volkan Cevher at the Laboratory for In
 formation and Inference Systems (LIONS) invites you to the following talk
 : Robust Estimation via Robust Gradient Estimation by Pradeep Ravikumar\,
   Professor at School of Computer Science\, Carnegie Mellon University.\n
 \nABSTRACT\nA common assumption in the training of machine learning system
 s is that the data is sufficiently clean and well-behaved: there are very 
 few or no outliers\, or that the distribution of the data does not have ve
 ry long tails. As machine learning finds wider usage\, these assumptions a
 re increasingly indefensible. The key question then is how to perform esti
 mation that is robust to departure from these assumptions\; and which has 
 been of classical interest\, with seminal contributions due to Box\, Tukey
 \, Huber\, Hampel\, and several others. Loosely\, there seemed to be a com
 putation-robustness tradeoff\, practical estimators did have strong robust
 ness guarantees\, while estimators with strong robustness guarantees were 
 computationally impractical.\n \nIn our work\, we provide a new class of 
 computationally-efficient class of estimators for risk minimization that a
 re provably robust to a variety of robustness settings\, such as arbitrary
  oblivious contamination\, and heavy-tailed data\, among others. Our workh
 orse is a novel robust variant of gradient descent\, and we provide condit
 ions under which our gradient descent variant provides accurate and robust
  estimators in any general convex risk minimization problem. These results
  provide some of the first computationally tractable and provably robust e
 stimators for general statistical models.\n \nJoint work with Adarsh Pras
 ad\, Arun Sai Suggala\, Sivaraman Balakrishnan.\n\nBio:\nPradeep Ravikumar
  is an Associate Professor in the Machine Learning Department\, School of 
 Computer Science at Carnegie Mellon University. His thesis has received ho
 norable mentions in the ACM SIGKDD Dissertation award and the CMU School o
 f Computer Science Distinguished Dissertation award. He is a Sloan Fellow\
 , a Siebel Scholar\, a recipient of the NSF CAREER Award\, and was Program
  Chair for the International Conference on Artificial Intelligence and Sta
 tistics (AISTATS) in 2013.\n \n\n 
LOCATION:MXF 1 https://plan.epfl.ch/?room==MXF%201
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR