Compressed Maximum Likelihood

Authors: Yi Hao, Alon Orlitsky

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

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper concerns functional estimation, where P is a distribution collection over a domain space Z, and f : P Q is a functional, mapping distributions in P into a space Q equipped with a pseudo-metric d.
Researcher Affiliation Academia 1Department of Electrical and Computer Engineering, University of California, San Diego, USA.
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper refers to drawing 'samples' from distributions for theoretical analysis, but it does not specify any publicly available datasets used for training or empirical evaluation.
Dataset Splits No The paper does not provide specific dataset split information (e.g., train/validation/test percentages or counts) as it is primarily theoretical.
Hardware Specification No The paper does not provide any specific hardware details used for running experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper does not contain specific experimental setup details such as hyperparameters, training configurations, or system-level settings, as it is a theoretical work.