BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Efficient scalable algorithms for adaptive data co
 llection
DTSTART:20170309T101500
DTEND:20170309T113000
DTSTAMP:20260407T020934Z
UID:3cee61959515e82977aa5b28b28382027312e2e2cc05c6a357611878
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Kevin Jamieson - UC Berkeley\nIC Faculty candidate\n\nAbst
 ract :\nIn many applications\, data-driven discovery is limited by the rat
 e of data collection: the skilled labor it takes to operate a pipette\, th
 e time to execute a long-running physics simulation\, the patience of an i
 nfant to remain still in an MRI\, or the cost of labeling large corpuses o
 f complex images. A powerful paradigm to extract the most information with
  such limited resources is active learning\, or adaptive data collection\,
  which leverages already-collected data to guide future measurements in a 
 closed loop. But being convinced that data-collection should be adaptive i
 s not the same thing as knowing how to adapt in a way that is both sample 
 efficient and reliable. In this talk\, I will present several examples of 
 my provably reliable -- and practical -- adaptive data collection algorith
 ms being applied in the real-world. In particular\, I will show how my ada
 ptive algorithms are used each week to crowd-source the winner of the New 
 Yorker Magazine Cartoon Caption Contest. I will also discuss my applicatio
 n of adaptive learning concepts at Google to accelerate the tuning of deep
  networks in a highly parallelized environment of thousands of GPUs.\n\nBi
 o :\nKevin Jamieson is a postdoctoral researcher working with Professor Be
 njamin Recht in the Department of Electrical Engineering and Computer Scie
 nces at the University of California\, Berkeley. He is interested in the t
 heory and practice of machine learning algorithms that sequentially collec
 t data using an adaptive strategy. This includes active learning\, multi-a
 rmed bandit problems\, and stochastic optimization. Kevin received his Ph.
 D. from the University of Wisconsin - Madison under the advisement of Robe
 rt Nowak. Prior to his doctoral work\, Kevin received his B.S. from the Un
 iversity of Washington\, and an M.S. from Columbia University\, both in el
 ectrical engineering.  \n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR