[Forum SIS] One World ABC Seminar: "Neural Approximate Sufficient Statistics, " Michael Gutmann - October 28
Umberto Picchini
umberto.picchini a gmail.com
Mar 26 Ott 2021 14:42:44 CEST
Dear all
it is time again for a new talk at the One WorldABC Seminar
<https://warwick.ac.uk/fac/sci/statistics/news/upcoming-seminars/abcworldseminar>!
Our next speaker will be Michael Gutmann
<https://michaelgutmann.github.io>, who will talk about /Neural
Approximate Sufficient Statistics
<https://openreview.net/pdf?id=SRDuJssQud>/, onThursday October 28, at
11.30am UK time, with an abstract reported below.
Coordinates to join the talk are below. However more generally please
*sign up to the dedicated **email list
<https://listserv.csv.warwick.ac.uk/mailman/listinfo/abc_world_seminar>***to
get updates about future One World ABC seminars.
https://ed-ac-uk.zoom.us/j/82567695825
<https://ed-ac-uk.zoom.us/j/82567695825>
Meeting ID: 825 6769 5825
Passcode: hq1z8WYx
We look forward to seeing you on Thursday,
best wishes,
The One World ABC Seminar Organisers.
---
*When*: Thursday, October 28, 11.30am UK Time
*Speaker*: Michael Gutmann <https://michaelgutmann.github.io>,
University of Edinburg
*Title*: Neural Approximate Sufficient Statistics
*Abstract*: My talk will first review the concept of sufficient
statistics and then explain that we can learn them by learning mutual
information maximizing representations. I will then explain how we used
the learned statistics to boost the performance of both classical and
recent methods for Bayesian parameter inference when the likelihood is
intractable but sampling from the model is possible.
The talk is based on the paper:
Neural Approximate Sufficient Statistics for Implicit Models. Y. Chen,
D. Zhang, M. Gutmann, A. Courville, and Z. Zhu. In International
Conference on Learning Representations (ICLR) 2021
https://openreview.net/pdf?id=SRDuJssQud
<https://openreview.net/pdf?id=SRDuJssQud>
-------------- parte successiva --------------
Un allegato HTML è stato rimosso...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20211026/d49e7889/attachment.html>
Maggiori informazioni sulla lista
Sis