Global to push GA events into
skip to main content

Title: Efficient convolutional sparse coding

Computationally efficient algorithms may be applied for fast dictionary learning solving the convolutional sparse coding problem in the Fourier domain. More specifically, efficient convolutional sparse coding may be derived within an alternating direction method of multipliers (ADMM) framework that utilizes fast Fourier transforms (FFT) to solve the main linear system in the frequency domain. Such algorithms may enable a significant reduction in computational cost over conventional approaches by implementing a linear solver for the most critical and computationally expensive component of the conventional iterative algorithm. The theoretical computational cost of the algorithm may be reduced from O(M.sup.3N) to O(MN log N), where N is the dimensionality of the data and M is the number of elements in the dictionary. This significant improvement in efficiency may greatly increase the range of problems that can practically be addressed via convolutional sparse representations.
Issue Date:
OSTI Identifier:
Los Alamos National Security, LLC LANL
Patent Number(s):
Application Number:
Contract Number:
Resource Relation:
Patent File Date: 2015 Mar 25
Research Org:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org:
Country of Publication:
United States

Other works cited in this record:

System and method for audio data compression and decompression using discrete wavelet transform (DWT)
patent, March 2007

Method and apparatus for distributed compressed sensing
patent, September 2007

Holographic data storage using oversampling and balanced codewords
patent, June 2011

Systems and methods for resolution-invariant image representation
patent, September 2013

Method for recognizing shapes and system implementing said method
patent, April 2014

Integrated circuit implementation of methods and apparatuses for monitoring occupancy of wideband GHz spectrum, and sensing respective frequency components of time-varying signals using sub-nyquist criterion signal sampling
patent, April 2016

Dictionary Learning with Large Step Gradient Descent for Sparse Representations
book, January 2012
  • Mailhé, Boris; Plumbley, Mark D.; Theis, Fabian
  • Latent Variable Analysis and Signal Separation, p. 231-238
  • DOI: 10.1007/978-3-642-28551-6_29

Alternating Direction Method with Self-Adaptive Penalty Parameters for Monotone Variational Inequalities
journal, August 2000
  • He, B. S.; Yang, H.; Wang, S. L.
  • Journal of Optimization Theory and Applications, Vol. 106, Issue 2, p. 337-356
  • DOI: 10.1023/A:1004603514434

Similar records in DOepatents and OSTI.GOV collections: