The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels

Authors: Florian Kalinke, Zoltan Szabo

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

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we prove that the minimax optimal rate of HSIC estimation on Rd for Borel measures containing the Gaussians with continuous bounded translation-invariant characteristic kernels is O n 1/2 .
Researcher Affiliation Academia Florian Kalinke Institute for Program Structures and Data Organization Karlsruhe Institute of Technology Karlsruhe, Germany florian.kalinke@kit.edu Zoltán Szabó Department of Statistics London School of Economics London, UK z.szabo@lse.ac.uk
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper is theoretical and does not mention providing open-source code for its methodology.
Open Datasets No The paper does not include experiments and thus does not use a training dataset. It focuses on theoretical bounds for distributions.
Dataset Splits No The paper does not include experiments and thus does not specify validation dataset splits.
Hardware Specification No The paper does not include experiments and thus does not provide hardware specifications.
Software Dependencies No The paper does not include experiments and thus does not provide specific software dependencies with version numbers.
Experiment Setup No The paper does not include experiments and thus does not provide details about an experimental setup like hyperparameters or training settings.