Sökning: onr:"swepub:oai:DiVA.org:kth-287767" >
Adaptive random fou...
-
Kammonen, Aku,1984-KTH,Numerisk analys, NA
(författare)
Adaptive random fourier features with metropolis sampling
- Artikel/kapitelEngelska2019
Förlag, utgivningsår, omfång ...
-
American Institute of Mathematical Sciences,2019
-
printrdacarrier
Nummerbeteckningar
-
LIBRIS-ID:oai:DiVA.org:kth-287767
-
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-287767URI
-
https://doi.org/10.3934/fods.2020014DOI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:ref swepub-contenttype
-
Ämneskategori:art swepub-publicationtype
Anmärkningar
-
QC 20201221
-
The supervised learning problem todetermine a neural network approximation $\mathbb{R}^d\ni x\mapsto\sum_{k=1}^K\hat\beta_k e^{{\mathrm{i}}\omega_k\cdot x}$with one hidden layer is studied asa random Fourier features algorithm. The Fourier features, i.e., the frequencies $\omega_k\in\mathbb{R}^d$,are sampled using an adaptive Metropolis sampler.The Metropolis test accepts proposal frequencies $\omega_k'$, having corresponding amplitudes $\hat\beta_k'$, with the probability$\min\big\{1, (|\hat\beta_k'|/|\hat\beta_k|)^\gamma\big\}$,for a certain positive parameter $\gamma$, determined by minimizing the approximation error for given computational work.This adaptive, non-parametric stochastic method leads asymptotically, as $K\to\infty$, to equidistributed amplitudes $|\hat\beta_k|$, analogous to deterministic adaptive algorithms for differential equations. The equidistributed amplitudes are shown to asymptotically correspond to the optimal density for independent samples in random Fourier features methods.Numerical evidence is provided in order to demonstrate the approximation properties and efficiency of the proposed algorithm. The algorithm is testedboth on synthetic data and a real-world high-dimensional benchmark.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Kiessling, JonasH-Ai AB, Grevgatan 23,114 53, Stockholm, Sweden
(författare)
-
Plecháč, PetrDepartment of Mathematical Sciences, University of Delaware, Newark, DE 19716, USA
(författare)
-
Sandberg, MattiasKTH,Numerisk analys, NA(Swepub:kth)u17r6d2m
(författare)
-
Szepessy, Anders,1960-KTH,Numerisk analys, NA(Swepub:kth)u1mrbma3
(författare)
-
KTHNumerisk analys, NA
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:Foundations of Data Science: American Institute of Mathematical Sciences0:0, s. 0-02639-8001
Internetlänk
Hitta via bibliotek
Till lärosätets databas