Busca avançada
Ano de início
Entree


Thin and Deep Gaussian Processes

Texto completo
Autor(es):
de Souza, Daniel Augusto ; Nikitin, Alexander ; John, S. T. ; Ross, Magnus ; Alvarez, Mauricio A. ; Deisenroth, Marc Peter ; Gomes, Joao P. P. ; Mesquita, Diego ; Mattos, Cesar Lincoln C.
Número total de Autores: 9
Tipo de documento: Artigo Científico
Fonte: ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017); v. N/A, p. 11-pg., 2023-01-01.
Resumo

Gaussian processes (GPs) can provide a principled approach to uncertainty quantification with easy-to-interpret kernel hyperparameters, such as the lengthscale, which controls the correlation distance of function values. However, selecting an appropriate kernel can be challenging. Deep GPs avoid manual kernel engineering by successively parameterizing kernels with GP layers, allowing them to learn low-dimensional embeddings of the inputs that explain the output data. Following the architecture of deep neural networks, the most common deep GPs warp the input space layer-by-layer but lose all the interpretability of shallow GPs. An alternative construction is to successively parameterize the lengthscale of a kernel, improving the interpretability but ultimately giving away the notion of learning lower-dimensional embeddings. Unfortunately, both methods are susceptible to particular pathologies which may hinder fitting and limit their interpretability. This work proposes a novel synthesis of both previous approaches: Thin and Deep GP (TDGP). Each TDGP layer defines locally linear transformations of the original input data maintaining the concept of latent embeddings while also retaining the interpretation of lengthscales of a kernel. Moreover, unlike the prior methods, TDGP induces non-pathological manifolds that admit learning lower-dimensional representations. We show with theoretical and experimental results that i) TDGP is, unlike previous models, tailored to specifically discover lower-dimensional manifolds in the input data, ii) TDGP behaves well when increasing the number of layers, and iii) TDGP performs well in standard benchmark datasets. (AU)

Processo FAPESP: 23/00815-6 - Reimaginando IA para um mundo em chamas
Beneficiário:Diego Parente Paiva Mesquita
Modalidade de apoio: Auxílio à Pesquisa - Regular