BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Research Office,Faculty & Staff
DESCRIPTION:Large-scale Optimization for Machine Learning\n\n\nAryan Mokhta
 ri\nPostdoctoral Associate\nMassachusetts Institute of Technology \n\nIn la
 rge-scale data science\, we train models for datasets containing massive nu
 mbers of samples. Training is often formulated as the solution of empirical
  risk minimization (ERM) problems which are optimization programs whose com
 plexity scales with the number of elements in the dataset. This motivates t
 he use of stochastic optimization techniques which\, alas\, come with their
  own set of limitations. In this talk\, we will discuss recent developments
  to accelerate the convergence of stochastic optimization through the explo
 itation of second-order information. In particular\, we present stochastic 
 variants of quasi-Newton methods which approximate the curvature of the obj
 ective function using stochastic gradient information. We will explain how 
 this leads to faster convergence and introduce an incremental method that e
 xploits memory to achieve a superlinear convergence rate. This is the bestk
 nown convergence rate for a stochastic optimization method. We will also co
 ver adaptive sample size schemes which rethink ERM as a collection of neste
 d ERM problems in which the dataset grows at a geometric rate -- as opposed
  to stochastic methods in which samples are processed sequentially. We show
  how second-order versions of adaptive sample size methods are guaranteed t
 o solve ERM problems to their statistical accuracy in just two passes over 
 the dataset. We further extend this idea to the nonconvex setting to come u
 p with computationally efficient methods for finding a local minimizer of E
 RM problems when the population risk is strongly Morse. \n\nAryan Mokhtari 
 is a Postdoctoral Associate in the Laboratory for Information and Decision 
 Systems (LIDS) at the Massachusetts Institute of Technology (MIT)\, since J
 anuary 2018. Before joining MIT\, he was a Research Fellow at the Simons In
 stitute for the Theory of Computing at the University of California\, Berke
 ley\, for the program on “Bridging Continuous and Discrete Optimization”\, 
 from August to December 2017. Prior to that\, he was a graduate student at 
 the University of Pennsylvania (Penn) where he received his M.Sc. and Ph.D.
  degrees in electrical and systems engineering in 2014 and 2017\, respectiv
 ely\, and his A.M. degree in statistics from the Wharton School in 2017. Dr
 . Mokhtari received his B.Sc. degree in electrical engineering from Sharif 
 University of Technology\, Tehran\, Iran\, in 2011. His research interests 
 include the areas of optimization\, machine learning\, and artificial intel
 ligence. His current research focuses on the theory and applications of con
 vex and non-convex optimization in large-scale machine learning and data sc
 ience problems. He has received a number of awards and fellowships\, includ
 ing Penn’s Joseph and Rosaline Wolf Award for Best Doctoral Dissertation in
  electrical and systems engineering and the Simons-Berkeley Fellowship.\n\n
 Seminar hosted by Data Science Institue
DTEND:20190219T160000Z
DTSTAMP:20260510T104142Z
DTSTART:20190219T150000Z
GEO:39.68018;-75.748505
LOCATION:Pearson Hall
SEQUENCE:0
SUMMARY:Data Science Seminar Series - Aryan Mokhtari
UID:tag:localist.com\,2008:EventInstance_4352760
URL:https://events.udel.edu/event/data_science_seminar_series_-_aryan_mokht
 ari
END:VEVENT
END:VCALENDAR