Sharp uniform convergence bounds through empirical centralization

Authors: Cyrus Cousins, Matteo Riondato

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experimental evaluation shows that our bounds greatly outperform non-centralized bounds and are extremely practical even at small sample sizes.
Researcher Affiliation Academia Cyrus Cousins Department of Computer Science Brown University Providence, RI 02912 ccousins@cs.brown.edu Matteo Riondato Department of Computer Science Amherst College Amherst, MA 01002 mriondato@amherst.edu
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes The code is included in the supplementary material.
Open Datasets No The paper describes generating samples: "We generated the samples ๐’™for our experiments from random distributions over โ„๐‘‘." It does not provide a link, DOI, or citation to a publicly available dataset for access.
Dataset Splits No The paper mentions varying sample size 'm' but does not specify explicit train/validation/test splits, percentages, or a method for creating such splits to ensure reproducibility.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper does not list any specific software dependencies with version numbers.
Experiment Setup Yes In all experiments, we used ๐›ฟ= 0.01 and ๐‘›= 32 (we comment on this choice below). The sample size ๐‘švaried from 4 (the minimum possible, due to Lemma 1) to 107.