Measures of distortion for machine learning

Authors: Leena Chennuru Vankadara, Ulrike von Luxburg

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the behavior of various distortion measures by conducting experiments in two different settings: 1) Dimensionality reduction 2) A pipeline consisting of dimensionality reduction followed by classification. We start with simulated data for which we know all ground truth parameters. In order to generate datasets of dimension D, we sample each coordinate independently from a specified 1-dimensional distribution.
Researcher Affiliation Academia Leena Chennuru Vankadara University of Tübingen Max Planck Institute for Intelligent Systems, Tübingen leena.chennuru@tuebingen.mpg.de Ulrike von Luxburg University of Tübingen Max Planck Institute for Intelligent Systems, Tübingen luxburg@informatik.uni-tuebingen.de
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide an explicit statement about releasing source code for the described methodology or a link to a code repository.
Open Datasets No The paper states: "We start with simulated data for which we know all ground truth parameters. In order to generate datasets of dimension D, we sample each coordinate independently from a specified 1-dimensional distribution." This indicates generated data rather than a publicly available dataset.
Dataset Splits No The paper does not explicitly provide details about training/validation/test dataset splits, percentages, or specific splitting methodologies for its experiments.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory) used for running its experiments.
Software Dependencies No The paper mentions various algorithms and models used (e.g., Isomap, PCA, SVM) but does not provide specific software names with version numbers for reproducibility (e.g., Python 3.x, PyTorch 1.x).
Experiment Setup Yes Classification is performed on the resulting embeddings using kernel SVM (with RBF kernel) and k NN classification algorithms.