Density Estimation by Total Variation Regularization

  title={Density Estimation by Total Variation Regularization},
  author={Ivan Mizera},
L1 penalties have proven to be an attractive regularization device for nonparametric regression, image reconstruction, and model selection. For function estimation, L1 penalties, interpreted as roughness of the candidate function measured by their total variation, are known to be capable of capturing sharp changes in the target function while still maintaining a general smoothing objective. We explore the use of penalties based on total variation of the estimated density, its square root, and… CONTINUE READING
Highly Cited
This paper has 24 citations. REVIEW CITATIONS
13 Citations
37 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 13 extracted citations


Publications referenced by this paper.
Showing 1-10 of 37 references

Comment on Hansen and Kooperberg: Spline Adaptation in Extended Linear Models,

  • R. Koenker, I. Mizera
  • Statistical Science,
  • 2002
Highly Influential
5 Excerpts

Local extremes, runs, strings and multiresolution,

  • P. L. Davies, A. Kovac
  • The Annals of Statistics,
  • 2001
Highly Influential
6 Excerpts

Using Specially Designed Exponential Families for Density Estimation,

  • B. Efron, R. Tibshirani
  • The Annals of Statistics,
  • 1996
Highly Influential
8 Excerpts

A nonparametric roughness penalty for probability densities,

  • I. J. Good
  • Nature
  • 1971
Highly Influential
7 Excerpts

Estimation of ( Non ) smooth densities by total variation penalized likelihood

  • M. Saunders
  • 2005

Estimation of nonsmooth densities by total variation penalized likelihood driven by the sparsity L1 information criterion,”

  • S. Sardy, P. Tseng
  • 2005
1 Excerpt

gss: An R Package for general smoothing splines,

  • C. Gu
  • 2005
1 Excerpt

nor1mix: Normal (1-d) Mixture Models Classes and Methods,” R package version 1.0-5,

  • M. Mächler
  • 2005
2 Excerpts

Similar Papers

Loading similar papers…