Label consistency in overfitted generalized $k$-means

Authors: Linfan Zhang, Arash Amini

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

Reproducibility Variable Result LLM Response
Research Type Experimental 3.3 Numerical experiments We first consider the (noiseless) line-circle model in R3, an example of mixture-of-curves.
Researcher Affiliation Academia Linfan Zhang Department of Statistics University of California, Los Angeles Los Angeles, CA 90095 linfanz@g.ucla.edu Arash A. Amini Department of Statistics University of California, Los Angeles Los Angeles, CA 90095 aaamini@ucla.edu
Pseudocode No The paper provides mathematical formulations and proofs but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes] See the supplemental material.
Open Datasets No The paper uses synthetic models (line-circle model, line-Gaussian model, circle-torus model) defined within the paper, which are not externally available datasets with concrete access information (e.g., URL, DOI, or specific citation to an established public dataset repository).
Dataset Splits No The paper states the total number of data points sampled for numerical experiments (e.g., n = 3000) but does not specify any train, validation, or test splits.
Hardware Specification No The paper states "Computing details are in the supplemental material" in its checklist, but the main body of the paper does not specify any particular hardware (e.g., GPU/CPU models, memory, or cluster specifications) used for the experiments.
Software Dependencies No The paper does not provide specific software names with version numbers for any libraries, frameworks, or programming languages used in the experiments.
Experiment Setup No The paper describes simulation parameters like sample size (n=3000), noise levels (σ=0.1, σ=1), and separation parameters (δ) for its numerical experiments. However, it explicitly states "We did not do data training" in its checklist, implying there are no machine learning-specific hyperparameters or system-level training settings.