[ABE-L] Ciclo de Palestras - PPGE-IM/UFRJ - 29 de abril

[Carlos Zanini]

Caros colegas,

A próxima palestra do Ciclo de Palestras do Programa de Pós-graduação em
Estatística (PPGE) da UFRJ ocorrerá *quarta-feira, 29 de abril,* no horário
das *15h00* às 16h30, Local: Laboratório de Sistemas Estocásticos (LSE),
Sala I-044-B, Centro de Tecnologia - UFRJ.

*Palestrante:* Michael Zhang (Hong Kong University)

*Título:* Revisiting Nonstationary Kernel Design for Multi-Output Gaussian
Processes

*Resumo: *Multi-output Gaussian processes (MOGPs) provide a Bayesian
framework for modeling non-linear functions with multiple outputs, in which
nonstationary kernels are essential for capturing input-dependent
variations in observations. However, from a spectral (dual) perspective,
existing nonstationary kernels inherit the inflexibility and
over-parameterization of their spectral densities due to the restrictive
spectral–kernel duality. To overcome this, we establish a generalized
spectral–kernel duality that enables fully flexible matrix-valued spectral
densities — albeit at the cost of quadratic parameter growth in the number
of outputs. To achieve linear scaling while retaining sufficient
expressiveness, we propose the multi-output low-rank nonstationary (MO-LRN)
kernel: by modeling the spectral density through a low-rank matrix whose
rows are independently parameterized by bivariate Gaussian mixtures.
Experiments on synthetic and real-world datasets demonstrate that MO-LRN
consistently outperforms existing MOGP kernels in regression, missing-data
interpolation, and imputation tasks.

Mais informações:
https://ppge.im.ufrj.br/ciclo-de-palestras-primeiro-semestre-de-2026/

Organizadores: Carlos Zanini e Daniel Ungaretti

Atenciosamente,
Carlos Tadeu Pagani Zanini

-- 
----------------------------------------------------------------------------------------
Carlos Tadeu Pagani Zanini
Professor Adjunto
Departamento de Métodos Estatísticos - UFRJ
SIAPE: 1146101
carloszanini em dme.ufrj.br
carloszanini em im.ufrj.br
https://sites.google.com/view/ctpzanini
-------------------------------------------------------------------------------------------
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20260427/0c9b1a67/attachment-0001.htm>