BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Neural likelihood-free inference - Yanzhi Chen\, University of Cam
 bridge
DTSTART:20240320T110000Z
DTEND:20240320T123000Z
UID:TALK213427@talks.cam.ac.uk
CONTACT:Isaac Reid
DESCRIPTION:Likelihood-free inference (LFI) is a technique for Bayesian in
 ference in implicit statistical models. Such models have wide application 
 in science and engineering\, from inferring the R-value of an epidemic\, t
 o analyzing a stochastic volatility model. In this reading group\, we will
  provide an introductory overview on LFI\, covering methods\, use cases an
 d challenges. Specifically\, we will focus on recent neural network-based 
 methods. No preliminary knowledge is assumed. \n\nNo reading is required\,
  but the following materials may be useful:\n\n[1] Neural posterior estima
 te: https://arxiv.org/abs/1605.06376\, NeurIPS 2016\n\n[2] Neural likeliho
 od estimate: https://arxiv.org/abs/1805.07226\, AISTATS 2019\n\n[3] Neural
  sufficient statistics: https://arxiv.org/abs/2010.10079\, ICLR 2021\n\n[4
 ] Review: https://www.pnas.org/doi/10.1073/pnas.1912789117\, PNAS 2020
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38.
END:VEVENT
END:VCALENDAR