PATHWISE COORDINATE OPTIMIZATION

@article{Friedman2007PATHWISECO,
  title={PATHWISE COORDINATE OPTIMIZATION},
  author={J. Friedman and T. Hastie and Holger Hofling and R. Tibshirani},
  journal={The Annals of Applied Statistics},
  year={2007},
  volume={1},
  pages={302-332}
}
  • J. Friedman, T. Hastie, +1 author R. Tibshirani
  • Published 2007
  • Mathematics
  • The Annals of Applied Statistics
  • We consider “one-at-a-time” coordinate-wise descent algorithms for a class of convex optimization problems. An algorithm of this kind has been proposed for the L1-penalized regression (lasso) in the literature, but it seems to have been largely ignored. Indeed, it seems that coordinate-wise algorithms are not often used in convex optimization. We show that this algorithm is very competitive with the well-known LARS (or homotopy) procedure in large lasso problems, and that it can be applied to… CONTINUE READING
    1,767 Citations

    Figures and Tables from this paper

    Convergence of cyclic coordinatewise l1 minimization
    • 7
    • PDF
    Pathwise Coordinate Optimization for Sparse Learning: Algorithm and Theory
    • 31
    • Highly Influenced
    • PDF
    A block coordinate gradient descent method for regularized convex separable optimization and covariance selection
    • 21
    • PDF
    Relative Interior Rule in Block-Coordinate Descent
    • 6
    • PDF
    A General Theory of Pathwise Coordinate Optimization for Nonconvex Sparse Learning ∗
    • Highly Influenced
    • PDF
    Variational Optimization
    • 29
    • PDF
    On the Nonasymptotic Convergence of Cyclic Coordinate Descent Methods
    • 100
    • PDF
    Sparse convex optimization methods for machine learning
    • 72
    • PDF

    References

    SHOWING 1-10 OF 52 REFERENCES
    A Maximum Likelihood Approach to Least Absolute Deviation Regression
    • Y. Li, G. Arce
    • Mathematics, Computer Science
    • EURASIP J. Adv. Signal Process.
    • 2004
    • 76
    • PDF
    A new approach to variable selection in least squares problems
    • 847
    • Highly Influential
    • PDF
    Least angle regression
    • 7,995
    • PDF
    Nonlinear total variation based noise removal algorithms
    • 12,678
    • PDF
    Adapting to Unknown Smoothness via Wavelet Shrinkage
    • 4,501
    • Highly Influential
    • PDF
    Regression Shrinkage and Selection via the Lasso
    • 30,813
    • PDF