[Todos] Doble Seminario de Probabilidad del DM.

[Manuel Saenz]

Les informamos que la semana próxima habrá *SESIÓN DOBLE *del
Seminario de Probabilidad del
Departamento de Matemática.

*PRIMERA CHARLA:*

*Fecha y hora: *Miércoles 6/11/2019, 12hs
*Lugar: *Sala de Conferencias, 2do Piso, Departamento de Matemática,
Pabellón 1
*Expositor: *Bernardo Nunes Borges de Lima (UFMG)
*Título: **The Constrained-degree percolation model*
*Abstract:* In the Constrained-degree percolation model on a graph
$(\V,\E)$ there are a sequence, $(U_e)_{e\in\E}$, of i.i.d. random
variables with distribution $U[0,1]$ and a positive integer $k$. Each bond
$e$ tries to open at time $U_e$, it succeeds if both its end-vertices would
have degrees at most $k-1$. We prove a phase transition theorem for this
model on the square lattice $\mathbb{L}^2$, as well on the d-ary regular
tree. We also prove that on the square lattice the infinite cluster is
unique in the supercritical phase. Joint work with R. Sanchis, D. dos
Santos, V. Sidoravicius and R. Teodoro.


*SEGUNDA CHARLA:*

*Fecha y hora: *Miércoles 20/11/2019, 14hs
*Lugar: *Aula a confirmar, Pabellón 1
*Expositor: *Martín Arjovsky (NYU)
*Título: **Towards Learning Causal Features*
*Abstract:* The talk will center on the deep relationship between out of
distribution generalization, causality, and invariant correlations. From
the study of this relationship, we introduce Invariant Risk Minimization
(IRM), a learning paradigm to estimate invariant correlations across
multiple training distributions. To achieve this goal, IRM learns a data
representation such that the optimal classifier, on top of that data
representation, matches for all training distributions. Through theory and
experiments, we show how the invariances learned by IRM relate to the
causal structures governing the data and enable out-of-distribution
generalization.
------------ próxima parte ------------
Se ha borrado un adjunto en formato HTML...
URL: <http://mailman.df.uba.ar/pipermail/todos/attachments/20191114/24941041/attachment.html>