Orlicz Random Fourier Features

Authors: Linda Chamakh, Emmanuel Gobet, Zoltán Szabó

JMLR 2020 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical To tackle this difficulty, we establish a finite-sample deviation bound for a general class of polynomial-growth functions under α-exponential Orlicz condition on the distribution of the sample. Instantiating this result for RFFs, our finite-sample uniform guarantee implies a.s. convergence with tight rate for arbitrary kernel with α-exponential Orlicz spectrum and any order of derivative.
Researcher Affiliation Collaboration Linda Chamakh EMAIL Emmanuel Gobet EMAIL Zolt an Szab o EMAIL CMAP, CNRS, Ecole Polytechnique, Institut Polytechnique de Paris 91128 Palaiseau, France Global Markets Quantitative Research BNP Paribas
Pseudocode No The paper describes mathematical proofs and theoretical analysis but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statements about providing open-source code or links to a code repository for the described methodology.
Open Datasets No The paper presents theoretical research, focusing on mathematical bounds and convergence rates for Orlicz Random Fourier Features, and does not involve experiments on specific datasets. Therefore, no information about publicly available datasets is provided.
Dataset Splits No The paper is theoretical and does not describe experiments using datasets, so there is no mention of dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and focuses on mathematical proofs and analysis; no computational experiments requiring specific hardware are described.
Software Dependencies No The paper is purely theoretical, providing mathematical proofs and analysis. It does not mention any software or libraries with version numbers used for computational experiments.
Experiment Setup No The paper is theoretical, presenting mathematical analysis and proofs. There are no experimental setups, hyperparameters, or training configurations described.