On the inability of Gaussian process regression to optimally learn compositional functions

16 May 2022

Papers citing "On the inability of Gaussian process regression to optimally learn compositional functions"

11 / 11 papers shown

Title
Support Collapse of Deep Gaussian Processes with Polynomial Kernels for a Wide Regime of Hyperparameters Daryna Chernobrovkina Steffen Grünewälder 51 0 0 15 Mar 2025
On strong posterior contraction rates for Besov-Laplace priors in the white noise model Emanuele Dolera Stefano Favaro Matteo Giordano 26 0 0 11 Nov 2024
How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning Arthur Jacot Seok Hoan Choi Yuxiao Wen AI4CE 91 2 0 08 Jul 2024
Deep Horseshoe Gaussian Processes Ismael Castillo Thibault Randrianarisoa BDL UQCV 42 5 0 04 Mar 2024
Deep Gaussian Process Priors for Bayesian Inference in Nonlinear Inverse Problems Kweku Abraham Neil Deo 20 5 0 21 Dec 2023
Deep Latent Force Models: ODE-based Process Convolutions for Bayesian Deep Learning Thomas Baldwin-McDonald Mauricio A. Álvarez 39 1 0 24 Nov 2023
Besov-Laplace priors in density estimation: optimal posterior contraction rates and adaptation M. Giordano 21 4 0 30 Aug 2022
What Can Be Learnt With Wide Convolutional Neural Networks? Francesco Cagnetta Alessandro Favero M. Wyart MLT 38 11 0 01 Aug 2022
Posterior contraction rates for constrained deep Gaussian processes in density estimation and classication F. Bachoc A. Lagnoux 21 4 0 14 Dec 2021
Posterior contraction for deep Gaussian process priors G. Finocchio Johannes Schmidt-Hieber 35 10 0 16 May 2021
Benefits of depth in neural networks Matus Telgarsky 142 602 0 14 Feb 2016