[Forum SIS] Seminar in Statistics LORENZO ROSASCO

Pierpaolo De Blasi pierpaolo.deblasi a unito.it
Ven 12 Nov 2021 14:24:50 CET 

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

Venerdi 19 Novembre 2021, alle ore 12.00, presso il Collegio Carlo Alberto,
in Piazza Arbarello 8, Torino, si terrā il seguente seminario:

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

Speaker: *Lorenzo Rosasco *(University of Genova & MIT)


Title: *Interpolation and learning with scale dependent kernels*

Abstract:
We study the learning properties of nonparametric ridge-less least squares.
In particular, we consider the common case of estimators defined by scale
dependent (Matern) kernels, and focus on the role scale and smoothness.
These estimators interpolate the data and the scale can be shown to control
their stability to noise and sampling.  Larger scales, corresponding to
smoother functions, improve stability with respect to sampling. However,
smaller scales, corresponding to more complex functions, improve stability
to noise. We will discuss to which extent these results can explain the
learning curves observed for large overparameterized models.  Our analysis
combines, probabilistic results with analytic techniques from interpolation
theory.
------------------------------------------------

In ottemperanza alle norme anti Covid, per partecipare in presenza č
necessario prenotarsi tramite il seguente form online:
https://forms.gle/236nC7S6NrVwHzEm8

Sarā possibile seguire il seminario anche in streaming:
Join Zoom Meeting
<https://us02web.zoom.us/j/82967941062?pwd=RGpFUmY2YzdLS2VyMnJTeCt5ODFVZz09>
Meeting ID: 829 6794 1062
Passcode: 846274


Il seminario č 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 č stato rimosso...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20211112/01152f4a/attachment.html>

Maggiori informazioni sulla lista Sis