Dimension-free empirical entropy estimation

Authors: Doron Cohen, Aryeh Kontorovich, Aaron Koolyk, Geoffrey Wolfer

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Moreover, we demonstrate that our empirical bounds are significantly sharper than the state-of-the-art bounds, for various natural distributions and non-trivial sample regimes. In Section 6, we compare the rates implied by Corollary 1 to the state of the art on various distributions.
Researcher Affiliation Academia Doron Cohen Department of Computer Science Ben-Gurion University of the Negev Beer-Sheva, Israel doronv@post.bgu.ac.il Aryeh Kontorovich Department of Computer Science Ben-Gurion University of the Negev Beer-Sheva, Israel karyeh@cs.bgu.ac.il Aaron Koolyk Department of Computer Science Hebrew University Jerusalem, Israel aaron.koolyk@mail.huji.ac.il Geoffrey Wolfer JSPS International Research Fellow Department of Computer and Information Sciences Tokyo University of Agriculture and Technology Tokyo, Japan geo-wolfer@m2.tuat.ac.jp
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code or include links to a code repository for the described methodology.
Open Datasets No The paper evaluates its bounds on theoretical distributions like mixtures of uniform distributions and zeta distributions, rather than real-world public datasets.
Dataset Splits No The paper does not describe the use of empirical datasets, and therefore no specific dataset split information (like train/validation/test percentages or counts) is provided.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used for the numerical computations that generated the results.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., Python 3.8, PyTorch 1.9) required to replicate the results.
Experiment Setup No The paper is primarily theoretical, deriving and comparing bounds for entropy estimation. It does not describe an experimental setup with specific hyperparameters, training configurations, or system-level settings for empirical evaluation of a model.