Probabilistic Bounds for Binary Classification of Large Data Sets

Authors: Věra Kůrková, M. Sanguineti
Publication year: 2020
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: Recent Advances in Big Data and Deep Learning
Projects: Capabilities and limitations of shallow and deep networks
Bibliographic citation: KŮRKOVÁ, Věra, SANGUINETI, M. Probabilistic Bounds for Binary Classification of Large Data Sets. In: ONETO, L., NAVARIN, N., SPERDUTI, A., ANGUITA, D., eds. Recent Advances in Big Data and Deep Learning. Cham: Springer, 2020, S. 309-319. Proceedings of the International Neural Networks Society. ISBN 978-3-030-16840-7. ISSN 2661-8141
Dostupné z: doi:10.1007/978-3-030-16841-4_32
DOI: 10.1007/978-3-030-16841-4_32
ID: 503127

Abstract

A probabilistic model for classification of task relevance is investigated. Correlations between randomly-chosen functions and network input-output functions are estimated. Impact of large data sets is analyzed from the point of view of the concentration of measure phenomenon. The Azuma-Hoeffding Inequality is exploited, which can be applied also when the naive Bayes assumption is not satisfied (i.e., when assignments of class labels to feature vectors are not independent).