SwePub
Sök i SwePub databas

  Extended search

Träfflista för sökning "WFRF:(Kammonen Aku 1984 ) srt2:(2019)"

Search: WFRF:(Kammonen Aku 1984 ) > (2019)

  • Result 1-2 of 2
Sort/group result
   
EnumerationReferenceCoverFind
1.
  • Kammonen, Aku, 1984-, et al. (author)
  • Adaptive random fourier features with metropolis sampling
  • 2019
  • In: Foundations of Data Science. - : American Institute of Mathematical Sciences. - 2639-8001. ; 0:0, s. 0-0
  • Journal article (peer-reviewed)abstract
    • 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.
  •  
2.
  •  
Skapa referenser, mejla, bekava och länka
  • Result 1-2 of 2
Type of publication
journal article (2)
Type of content
peer-reviewed (2)
Author/Editor
Sandberg, Mattias (2)
Plechác, Petr (2)
Szepessy, Anders, 19 ... (2)
Kammonen, Aku, 1984- (2)
Kiessling, Jonas (1)
University
Royal Institute of Technology (2)
Language
English (2)
Research subject (UKÄ/SCB)
Natural sciences (2)
Year
2019 (2)Undo refine

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Close

Copy and save the link in order to return to this view