A Dynamic Programming Algorithm for the Fused Lasso and L 0-Segmentation

@inproceedings{Johnson2013ADP,
  title={A Dynamic Programming Algorithm for the Fused Lasso and L 0-Segmentation},
  author={Nicholas Alexander Johnson},
  year={2013}
}
We propose a dynamic programming algorithm for the one-dimensional Fused Lasso Signal Approximator (FLSA). The proposed algorithm has a linear running time in the worst case. A similar approach is developed for the task of least squares segmentation, and simulations indicate substantial performance improvement over existing algorithms. Examples of R and C implementations are provided in the online Supplementary materials, posted on the journal web site. 

Citations

Publications citing this paper.
SHOWING 1-10 OF 61 CITATIONS

Trend-Filtered Projection for Principal Component Analysis

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Direct Algorithm for Optimization Problems With the Huber Penalty

  • IEEE Transactions on Medical Imaging
  • 2018
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Constrained estimation via the fused lasso and some generalizations

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A deconvolution path for mixtures

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Total Variation on a Tree

  • SIAM J. Imaging Sciences
  • 2015
VIEW 9 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2011
2019

CITATION STATISTICS

  • 14 Highly Influenced Citations

  • Averaged 11 Citations per year from 2017 through 2019