Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and Smoothness

Authors: George Wynne, François-Xavier Briol, Mark Girolami

JMLR 2021 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we study the properties of Gaussian process means when the smoothness of the model and the likelihood function are misspecified. In this setting, an important theoretical question of practical relevance is how accurate the Gaussian process approximations will be given the chosen model and the extent of the misspecification. The main results in this paper are Theorem 1, Theorem 2, Theorem 4 and Theorem 7 which, respectively, concern the cases when a likelihood reflecting no noise is correctly assumed, a Gaussian likelihood is correctly assumed, a Gaussian likelihood is incorrectly assumed and a likelihood of no noise is assumed but there is arbitrary corruption.
Researcher Affiliation Academia George Wynne EMAIL Department of Mathematics Imperial College London London, SW7 2AZ, UK François-Xavier Briol EMAIL Department of Statistical Science University College London London, WC1E 7HB, UK Mark Girolami EMAIL Department of Engineering University of Cambridge Cambridge, CB2 1PZ, UK
Pseudocode No The paper focuses on theoretical convergence guarantees, theorems, and proofs. There are no structured pseudocode or algorithm blocks explicitly labeled as such within the main text or appendices.
Open Source Code No The paper does not contain any explicit statements about releasing source code for the methodology described, nor does it provide links to any code repositories.
Open Datasets No The paper is theoretical, focusing on convergence guarantees for Gaussian process means. It does not conduct experiments on specific datasets and therefore does not provide access information for any open datasets.
Dataset Splits No The paper is theoretical and does not involve experimental evaluation on datasets, thus no dataset split information (training, validation, test splits) is provided.
Hardware Specification No The paper is theoretical and does not involve experimental computation that would require specific hardware specifications.
Software Dependencies No The paper is theoretical and focuses on mathematical proofs and convergence guarantees. It does not describe an experimental setup that would necessitate listing specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not present experimental results. Therefore, it does not provide details on experimental setup, hyperparameters, or training configurations.