Corpus ID: 119308178

Global Error Bounds and Linear Convergence for Gradient-Based Algorithms for Trend Filtering and 𝓁1-Convex Clustering

@article{Ho2019GlobalEB,
  title={Global Error Bounds and Linear Convergence for Gradient-Based Algorithms for Trend Filtering and 𝓁1-Convex Clustering},
  author={Nhat Ho and Tianyi Lin and Michael I. Jordan},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.07462}
}
  • Nhat Ho, Tianyi Lin, Michael I. Jordan
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • We propose a class of first-order gradient-type optimization algorithms to solve structured \textit{filtering-clustering problems}, a class of problems which include trend filtering and $\ell_1$-convex clustering as special cases. Our first main result establishes the linear convergence of deterministic gradient-type algorithms despite the extreme ill-conditioning of the difference operator matrices in these problems. This convergence result is based on a convex-concave saddle point formulation… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 41 REFERENCES
    Nonlinear total variation based noise removal algorithms
    • 12,343
    • PDF
    Introductory Lectures on Convex Optimization - A Basic Course
    • 3,968
    • Highly Influential
    • PDF
    Splitting Methods for Convex Clustering
    • 147
    • Highly Influential
    • PDF
    Stochastic Variance Reduction Methods for Saddle-Point Problems
    • 95
    • PDF
    Adaptive piecewise polynomial estimation via trend filtering
    • 222
    • PDF
    Error Bounds, Quadratic Growth, and Linear Convergence of Proximal Methods
    • 134
    • PDF
    Sparsity and smoothness via the fused lasso
    • 1,998
    • PDF
    Fast and Flexible ADMM Algorithms for Trend Filtering
    • 61
    • Highly Influential
    • PDF
    Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization
    • 428
    • Highly Influential
    • PDF
    Linearly convergent away-step conditional gradient for non-strongly convex functions
    • 66
    • PDF