[ABE-L] Divulgação Seminário PPGEst-UFRGS

[Fábio Mariano Bayer]

Prezados,

Temos o prazer de convidar a todos para mais um seminário do Ciclo de
Seminários 2021 do Programa de Pós-Graduação em Estatística da UFRGS
(PPGEst-UFRGS). Informações abaixo:

*Evento:* Ciclo de Seminários 2021 do PPGEst-UFRGS

*Palestrante:* Dr. Yining Chen (London School of Economics-UK)

*Título:* Multiple change-points and change-point-like features detection:
binary segmentation, wild binary segmentation, narrowest-over-threshold and
beyond

*Resumo:* In this talk, we focus on the problem of change-points detection
and estimation in the univariate setting. Some popular approaches, such as
binary segmentation and wild binary segmentation will be revisited, with a
discussion on their advantages and limitations. We will also present the
narrowest-over-threshold (NOT) approach, which is a generic and flexible
methodology that can handle scenarios such as change-points in the
piecewise-constant signal model, kinks in the piecewise-linear signal
model, and other similar irregularities, which we also refer to as
generalised change-points. NOT offers highly competitive performance when
being applied together with some information criteria. If time permits, we
shall also talk about some recent extensions, as well as the problem of
change-point detection in the multi/high-dimensional settings.

*Data:* 13 de setembro de 2021 (segunda-feira)

*Horário:* 14h00 às 15:20 (60 min de apresentação e 20 min para perguntas)

*Local:* Ambiente virtual Google Meet. Link:
http://meet.google.com/jrj-vjpr-moy

*Moderador:* Prof. Flávio Ziegelmann (PPGEst-UFRGS)

Contamos com a presença de todos.

PPGEst-UFRGS

Fábio Bayer


"A big computer, a complex algorithm and a long time does not equal
science." Robert Gentleman
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20210909/e9b54550/attachment.htm>