BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Stein Discrepancy - Sebastian Ober (University of Cambridge)
DTSTART:20190128T140000Z
DTEND:20190128T153000Z
UID:TALK119455@talks.cam.ac.uk
CONTACT:75379
DESCRIPTION:Recently\, Stein discrepancy-based methods have become popular
  tools for machine learning applications\, including verifying the converg
 ence of MCMC [1]\, goodness-of-fit tests [2][3]\, and variational inferenc
 e [4][5]. Although Stein's method has been long-known\, widespread use was
  limited by an intractable optimization over a difficult  function space. 
 However\, the recent development of the kernelized Stein discrepancy (KSD)
  [2][3] has circumvented this difficulty. Our talk will give a theoretical
  introduction to the Stein discrepancy and KSD. We will then introduce two
  recent applications of the Stein discrepancy to machine learning problems
 . The first of these\, Stein variational gradient descent (SVGD) [4]\, sho
 ws how to apply the KSD to variational inference.\nWe conclude by discussi
 ng the Stein variational autoencoder (Stein VAE) [5]\, which applies SVGD 
 to VAE learning. \n\nPapers that are important for the talk:\n\n\n[2] Chwi
 alkowski\, K.\, Strathmann\, H.\, and Gretton\, A. A kernel test of goodne
 ss of fit. In ICML\, 2016. https://arxiv.org/abs/1602.02964\n\n[4] Liu\, Q
 . and Wang\, D. Stein variational gradient descent: A general purpose Baye
 sian inference algorithm. In NIPS\, 2016.\nhttps://arxiv.org/abs/1608.0447
 1\n\n\nAdditional Recommended reading:\n\n[1] Gorham\, J. and Mackey\, L. 
 Measuring sample quality with Stein's method. In NIPS\, pp. 226-234\, 2015
 . https://arxiv.org/abs/1506.03039\n-- Note: we will only be discussing up
  to and including section 3\n\n[3] Liu\, Q.\, Lee\, J.\, and Jordan\, M. I
 . A kernelized Stein discrepancy for goodness-of-fit tests. In ICML\, 2016
 .\nhttps://arxiv.org/abs/1602.03253\n-- Note: this is essentially the same
  paper as [2]\, which is what we will present\n\n\n[5] Pu\, Y.\, Gan\, Z.\
 , Henao\, R.\, Li\, C.\, Han\, S.\, and Carin\, L. VAE learning with Stein
  variational gradient descent. In NIPS\, 2017. \nhttps://arxiv.org/abs/170
 4.05155
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR