Generalization Properties of Learning with Random Features

Authors: Alessandro Rudi, Lorenzo Rosasco

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Theoretical findings are complemented by numerical simulation validating the bounds. ... In Figure 3, the theoretical and estimated behavior of the excess risk, λ and M with respect to n are reported together with their standard deviation over 100 repetitions. The experiment shows that the predictions by Thm. 3 are accurate, since the theoretical predictions estimations are within one standard deviation from the values measured in the simulation.
Researcher Affiliation Academia Alessandro Rudi INRIA Sierra Project-team, Ecole Normale Sup erieure, Paris, 75012 Paris, France alessandro.rudi@inria.fr Lorenzo Rosasco University of Genova, Istituto Italiano di Tecnologia, Massachusetts Institute of Technology. lrosasco@mit.edu
Pseudocode No The paper does not contain any sections or figures explicitly labeled "Pseudocode" or "Algorithm", nor does it present any structured algorithm blocks.
Open Source Code No The paper does not contain any statements about releasing open-source code for the methodology described, nor does it provide links to any code repositories.
Open Datasets No The paper constructs a synthetic dataset based on a "spline kernel of order q" and a uniform distribution on [0, 1]. It does not use a publicly available dataset with concrete access information (link, DOI, or specific citation to a repository).
Dataset Splits No The paper describes a numerical simulation where the KRR estimator is computed, and then the RF-KRR estimator selects the number of features M to obtain an excess risk within a certain percentage of KRR. It does not specify traditional train/validation/test dataset splits (e.g., 80/10/10 percentages or specific sample counts) that are needed for reproducibility.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments, such as GPU models, CPU types, or memory specifications.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., programming languages, libraries, frameworks, or solvers).
Experiment Setup Yes In Figure 3, the theoretical and estimated behavior of the excess risk, λ and M with respect to n are reported together with their standard deviation over 100 repetitions. Parameters r = 11/16, γ = 1/8 (top), and r = 7/8, γ = 1/4 (bottom).