Počet záznamů: 1

Damped Gauss-Newton algorithm for nonnegative Tucker Decomposition

  1. 1.
    0363810 - UTIA-B 2012 RIV FR eng C - Konferenční příspěvek (zahraniční konf.)
    Phan, A. H. - Tichavský, Petr - Cichocki, A.
    Damped Gauss-Newton algorithm for nonnegative Tucker Decomposition.
    2011 IEEE Statistical Signal Processing Workshop (SSP) Proceedings. Nice: IEEE Signal Processing Society, 2011, s. 669-672. ISBN 978-1-4577-0568-7.
    [2011 IEEE Statistical Signal Processing Workshop (SSP). Nice (FR), 28.06.2011-30.06.2011]
    Grant CEP: GA MŠk 1M0572; GA ČR GA102/09/1278
    Výzkumný záměr: CEZ:AV0Z10750506
    Klíčová slova: nonnegative Tucker decomposition * low-rank approximation * face clustering
    Kód oboru RIV: BB - Aplikovaná statistika, operační výzkum
    http://library.utia.cas.cz/separaty/2011/SI/tichavsky-damped gauss-newton algorithm for nonnegative tucker decomposition.pdf http://library.utia.cas.cz/separaty/2011/SI/tichavsky-damped gauss-newton algorithm for nonnegative tucker decomposition.pdf

    Algorithms based on alternating optimization for nonnegative Tucker decompositions (NTD) such as ALS, multiplicative least squares, HALS have been confirmed effective and efficient. However, those algorithms often converge very slowly. To this end, we propose a novel algorithm for NTD using the Levenberg-Marquardt technique with fast computation method to construct the approximate Hessian and gradient without building up the large-scale Jacobian. The proposed algorithm has been verified to overwhelmingly outperform “state-of-the-art” NTD algorithms for difficult benchmarks, and application of face clustering.
    Trvalý link: http://hdl.handle.net/11104/0199466