Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning

Authors: François Denis, Mattias Gybels, Amaury Habrard

ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments demonstrate that these bounds are tight and that they significantly improve existing bounds. These bounds are evaluated on a benchmark made of 11 problems extracted from the PAutoma C challenge (Verwer et al., 2012).
Researcher Affiliation Academia Aix Marseille Universit e, CNRS, LIF, 13288 Marseille Cedex 9, FRANCE and Universit e Jean Monnet de Saint-Etienne, CNRS, La HC, 42000 Saint-Etienne Cedex 2, FRANCE
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described. There are no explicit code release statements or repository links.
Open Datasets Yes These bounds are evaluated on a benchmark made of 11 problems extracted from the PAutoma C challenge (Verwer et al., 2012).
Dataset Splits No The paper does not explicitly provide training/test/validation dataset splits. It mentions using a 'sample' for evaluation but does not specify how this sample is partitioned into distinct train, validation, and test sets for model training and evaluation.
Hardware Specification No The paper does not provide specific hardware details. It only vaguely mentions 'computing resources' without any model numbers, processor types, or memory details.
Software Dependencies No The paper mentions 'standard SVD algorithms available from Num Py or Sci Py' but does not specify version numbers for these software dependencies, which is required for reproducibility.
Experiment Setup No The paper focuses on theoretical bounds and their empirical validation. It does not provide specific experimental setup details such as hyperparameter values, training configurations, or system-level settings for a learning model.