Kernel quadrature with DPPs

Authors: Ayoub Belhadji, Rémi Bardenet, Pierre Chainais

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we experimentally compare DPPs to existing kernel-based quadratures such as herding, Bayesian quadrature, or leverage score sampling. Numerical results confirm the interest of DPPs, and even suggest faster rates than our bounds in particular cases. 5 Numerical simulations
Researcher Affiliation Academia Ayoub Belhadji, Rémi Bardenet, Pierre Chainais Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRISt AL, Villeneuve d Ascq, France {ayoub.belhadji, remi.bardenet, pierre.chainais}@univ-lille.fr
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper defines mathematical spaces and kernels (e.g., 'uniform measure on X = [0, 1]', 'Gaussian measure on X = R') for its numerical simulations, but does not use or provide access information for a distinct publicly available or open dataset.
Dataset Splits No The paper performs numerical simulations based on mathematical constructs rather than using empirical datasets with explicit train/validation/test splits. Therefore, no specific dataset split information for validation is provided.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers needed to replicate the experiments.
Experiment Setup Yes We take N [5, 50]. Figures 1a and 1b show log-log plots of the worst case quadrature error w.r.t. N, averaged over 50 samples for each point, for s {1, 3}. We take N [5, 1000] and s = 1. regularization parameter λ {0, 0.1, 0.2}