[Forum SIS] Seminar in Statistics GONZALO MENA

[Pierpaolo De Blasi]

SEMINARS IN STATISTICS @ COLLEGIO CARLO ALBERTO
<https://www.carloalberto.org/events/category/seminars/seminars-in-statistics/?tribe-bar-date=2019-09-01>

Venerdi 26 Novembre 2021, alle ore 12.00, presso il Collegio Carlo Alberto,
in Piazza Arbarello 8, Torino, si terrà il seguente seminario:

------------------------------------------------

Speaker: *Gonzalo Mena *(University of Oxford)


Title: *On the unreasonable effectiveness of Sinkhorn algorithm for
learning permutations and entropic optimal transport*

Abstract:
Sinkhorn's algorithm realizes the solution of entropy-regularized linear
programs on certain matrix polytopes. In the past years, the interest in
this algorithm has grown considerably because of its usefulness as a tool
for the modeling of permutations, and because of its fundamental role in
the solution of an entropic optimal transport problem, also called the
Schrödinger bridge. In this talk, I will give an overview of my work in
relation to these two areas.
First, regarding entropic optimal transport, I will argue that this tool is
valuable for deriving sensible statistical procedures. Indeed, we show that
it enjoys a substantially better sample complexity compared to optimal
transport, which suffers from the curse of dimensionality. Also, in the
more applied setup of model-based clustering we show that it can be used as
an alternative to the log-likelihood, since it has fewer bad local optima.
Based on this observation, we develop a new algorithm, Sinkhorn-EM, in
which we only modify the E-step to solve an Entropic Optimal Transport
problem. Our algorithm is shown to attain better practical performance.
Second, regarding permutations, I will describe some successful
applications in Deep Learning, and in neuroscience, for the inference of
neural identities in C.elegans worms.
Links
https://arxiv.org/abs/1802.08665
https://arxiv.org/abs/1905.11882
https://arxiv.org/abs/2006.16548
------------------------------------------------

In ottemperanza alle norme anti Covid, per partecipare in presenza è
necessario prenotarsi tramite il seguente form online:
https://forms.gle/XyyJ3JaqTeZLi92A6

Sarà possibile seguire il seminario anche in streaming:
Join Zoom Meeting
<https://us02web.zoom.us/j/84926221121?pwd=eDdycEV3M2VVVU1FSEszM000eDlIdz09>
Meeting ID: 849 2622 1121
Passcode: 899297


Il seminario è organizzato dalla "de Castro" Statistics Initiative

www.carloalberto.org/stats

Cordiali saluti,
Pierpaolo De Blasi
---
University of Torino & Collegio Carlo Alberto

carloalberto.org/pdeblasi
<https://sites.google.com/a/carloalberto.org/pdeblasi/>
-------------- parte successiva --------------
Un allegato HTML è stato rimosso...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20211122/37dcecc7/attachment.html>