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

Authors: Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We rigorously prove that deep Gaussian process priors can outperform Gaussian process priors if the target function has a compositional structure. To this end, we study information-theoretic lower bounds for posterior contraction rates for Gaussian process regression in a continuous regression model.
Researcher Affiliation Academia Matteo Giordano Department of Statistics University of Oxford matteo.giordano@stats.ox.ac.uk Kolyan Ray Department of Mathematics Imperial College London kolyan.ray@imperial.ac.uk Johannes Schmidt-Hieber Department of Applied Mathematics University of Twente a.j.schmidt-hieber@utwente.nl
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statement about making source code for the described methodology publicly available, nor does it provide a link to a code repository.
Open Datasets No The paper is theoretical and does not conduct empirical studies with datasets, therefore it does not mention publicly available training datasets.
Dataset Splits No The paper is theoretical and does not conduct empirical studies, therefore it does not provide training/test/validation dataset splits.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not provide specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training settings.