Adaptivity to local smoothness and dimension in kernel regression

Samory Kpotufe; Vikas K. Garg

Adaptivity to local smoothness and dimension in kernel regression

Samory Kpotufe, Vikas K. Garg

Ei julkaistu Aalto-yliopiston affiliaatiolla

Tutkimustuotos: Lehtiartikkeli › Conference article › Scientific › vertaisarvioitu

23 Sitaatiot (Scopus)

Abstrakti

We present the first result for kernel regression where the procedure adapts locally at a point x to both the unknown local dimension of the metric space χ and the unknown Hölder-continuity of the regression function at x. The result holds with high probability simultaneously at all points x in a general metric space χ of unknown structure.

Alkuperäiskieli	Englanti
Julkaisu	Advances in Neural Information Processing Systems
Tila	Julkaistu - 2013
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	IEEE Conference on Neural Information Processing Systems - Lake Tahoe, Yhdysvallat Kesto: 5 jouluk. 2013 → 10 jouluk. 2013

Muut tiedostot ja linkit

Link to publication in Scopus

Siteeraa tätä

@article{f0abb79174ac46d7be29f20a85442ffa,

title = "Adaptivity to local smoothness and dimension in kernel regression",

abstract = "We present the first result for kernel regression where the procedure adapts locally at a point x to both the unknown local dimension of the metric space χ and the unknown H{\"o}lder-continuity of the regression function at x. The result holds with high probability simultaneously at all points x in a general metric space χ of unknown structure.",

author = "Samory Kpotufe and Garg, {Vikas K.}",

year = "2013",

language = "English",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Morgan Kaufmann Publishers",

note = "IEEE Conference on Neural Information Processing Systems, NIPS ; Conference date: 05-12-2013 Through 10-12-2013",

}

TY - JOUR

T1 - Adaptivity to local smoothness and dimension in kernel regression

AU - Kpotufe, Samory

AU - Garg, Vikas K.

PY - 2013

Y1 - 2013

N2 - We present the first result for kernel regression where the procedure adapts locally at a point x to both the unknown local dimension of the metric space χ and the unknown Hölder-continuity of the regression function at x. The result holds with high probability simultaneously at all points x in a general metric space χ of unknown structure.

AB - We present the first result for kernel regression where the procedure adapts locally at a point x to both the unknown local dimension of the metric space χ and the unknown Hölder-continuity of the regression function at x. The result holds with high probability simultaneously at all points x in a general metric space χ of unknown structure.

UR - http://www.scopus.com/inward/record.url?scp=84899004232&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84899004232

SN - 1049-5258

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - IEEE Conference on Neural Information Processing Systems

Y2 - 5 December 2013 through 10 December 2013

ER -

Adaptivity to local smoothness and dimension in kernel regression

Abstrakti

Muut tiedostot ja linkit

Sormenjälki

Siteeraa tätä