Multiplicative updates for optimization problems with dynamics.

janelia7_blocks-janelia7_biblio_header | block
IEEE Xplore. 2018 Apr 16;. doi: 10.1109/ACSSC.2017.8335723
Multiplicative updates for optimization problems with dynamics. Druckmann LabPodgorski Lab
Kazemipour Abbas, Babadi Behtash, wu m, Podgorski K, Druckmann Shaul
janelia7_blocks-janelia7_biblio_abstract | block

Abstract

We consider the problem of optimizing general convex objective functions with nonnegativity constraints. Using the Karush-Kuhn-Tucker (KKT) conditions for the nonnegativity constraints we will derive fast multiplicative update rules for several problems of interest in signal processing, including non-negative deconvolution, point-process smoothing, ML estimation for Poisson Observations, nonnegative least squares and nonnegative matrix factorization (NMF). Our algorithm can also account for temporal and spatial structure and regularization. We will analyze the performance of our algorithm on simultaneously recorded neuronal calcium imaging and electrophysiology data.

node:body | entity_field

Previously published on December 15, 2017 as bioRxiv PrePrint https://dx.doi.org/10.1101/234526

janelia7_blocks-janelia7_biblio_authors | block

Janelia Authors

Kaspar Podgorski
Shaul Druckmann
janelia7_blocks-janelia7_biblio_tools | block