1 Sitaatiot (Scopus)
60 Lataukset (Pure)

Abstrakti

We apply network Lasso to semi-supervised regression problems involving network-structured data. This approach lends quite naturally to highly scalable learning algorithms in the form of message passing over an empirical graph which represents the network structure of the data. By using a simple non-parametric regression model, which is motivated by a clustering hypothesis, we provide an analysis of the estimation error incurred by network Lasso. This analysis reveals conditions on the network structure and the available training data which guarantee network Lasso to be accurate. Remarkably, the accuracy of network Lasso is related to the existence of suciently large network flows over the empirical graph. Thus, our analysis reveals a connection between network Lasso and maximum network flow problems.
AlkuperäiskieliEnglanti
OtsikkoProceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) 2019, Naha, Okinawa, Japan
KustantajaJMLR
Sivut380-387
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Artificial Intelligence and Statistics - Naha, Japani
Kesto: 16 huhtik. 201918 huhtik. 2019
Konferenssinumero: 22

Julkaisusarja

NimiProceedings of Machine Learning Research
KustantajaPMLR
Vuosikerta89
ISSN (elektroninen)1938-7228

Conference

ConferenceInternational Conference on Artificial Intelligence and Statistics
LyhennettäAISTATS
Maa/AlueJapani
KaupunkiNaha
Ajanjakso16/04/201918/04/2019

Sormenjälki

Sukella tutkimusaiheisiin 'Analysis of Network Lasso for Semi-Supervised Regression'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä