Privately Learning Smooth Distributions on the Hypercube by Projections

Authors: Clément Lalanne, Sébastien Gadat

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The contributions of this article are two-fold: Firstly, it generalizes the one-dimensional results of (Lalanne et al., 2023b) to non-integer levels of smoothness and to a high-dimensional setting... Secondly, this article presents a private strategy of estimation that is data-driven... This is achieved by adapting the Lepskii method for private selection, by adding a new penalization term that makes the estimation privacy-aware.
Researcher Affiliation Academia 1Toulouse School of Ecolomics, Universit e Toulouse 1 Capitole, Toulouse, France.
Pseudocode No No structured pseudocode or algorithm blocks were found in the paper.
Open Source Code No The paper does not provide concrete access to source code for the methodology described. It is a theoretical paper and does not mention any code release.
Open Datasets No The paper is theoretical and does not conduct experiments on specific datasets, therefore no public access information for a dataset is provided.
Dataset Splits No The paper is theoretical and does not conduct experiments with datasets, so no specific dataset split information for training, validation, or testing is provided.
Hardware Specification No The paper is theoretical and does not describe any experimental setup involving specific hardware or computational resources.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies or versions required to replicate its findings.
Experiment Setup No The paper is theoretical and describes mathematical formulations and proofs rather than an empirical experimental setup with hyperparameters or training configurations.