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; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1]

On Regularized Radon-Nikodym Differentiation

Authors: Duc Hoan Nguyen, Werner Zellinger, Sergei Pereverzyev

JMLR 2024 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our theoretical results are illustrated by numerical simulations. Finally, we present some numerical illustrations supporting our theoretical results.
Researcher Affiliation Academia Duc Hoan Nguyen EMAIL Johann Radon Institute for Computational and Applied Mathematics Austrian Academy of Sciences Altenberger Straße 69, 4040 Linz, Austria University of Lorraine, CNRS, CRAN, Nancy, F-54000, France Werner Zellinger EMAIL Sergei Pereverzyev EMAIL Johann Radon Institute for Computational and Applied Mathematics Austrian Academy of Sciences Altenberger Straße 69, 4040 Linz, Austria
Pseudocode Yes βλ,l X,0 = 0, βλ,l X = (nλI + K) 1 nλβλ,l 1 X + F , l = 1, 2, . . . , k.
Open Source Code No The paper does not provide any explicit statements about the release of source code or links to a code repository for the methodology described.
Open Datasets No In our examples, we simulate inputs Xp = (x1, x2, . . . , xn) to be sampled from the normal distribution p N(2, 5), while the inputs Xq = (x 1, x 2, . . . , x m) are sampled from the normal distribution q N(µq, 0.5) with µq = {2, 3, 4}.
Dataset Splits No The paper describes generating synthetic data by sampling from normal distributions and specifies sample sizes as m = n = 100. It does not refer to splitting a pre-existing dataset into training, validation, or test sets.
Hardware Specification No The paper does not provide specific hardware details used for running its experiments.
Software Dependencies No The paper does not provide specific software dependency details, such as library names with version numbers.
Experiment Setup Yes The algorithm Eq. 35 has been implemented with m = n = 100 and k = {1, 2, 3, 5, 10}. The regularization parameter λ is chosen by the so-called quasi-optimality criterion... we choose λ0 = 0.9, ϱ = 9q 1 9, and w = 9, such that λι [0.1, 0.9].