Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Laplacian smoothing gradient descent

Laplacian smoothing gradient descent We propose a class of very simple modifications of gradient descent and stochastic gradient descent leveraging Laplacian smoothing. We show that when applied to a large variety of machine learning problems, ranging from logistic regression to deep neural nets, the proposed surrogates can dramatically reduce the variance, allow to take a larger step size, and improve the generalization accuracy. The methods only involve multiplying the usual (stochastic) gradient by the inverse of a positive definitive matrix (which can be computed efficiently by FFT) with a low condition number coming from a one-dimensional discrete Laplacian or its high-order generalizations. Given any vector, e.g., gradient vector, Laplacian smoothing preserves the mean and increases the smallest component and decreases the largest component. Moreover, we show that optimization algorithms with these surrogates converge uniformly in the discrete Sobolev Hσp\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$H_\sigma ^p$$\end{document} sense and reduce the optimality gap for convex optimization problems. The code is available at: https://github.com/BaoWangMath/LaplacianSmoothing-GradientDescent. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Research in the Mathematical Sciences Springer Journals

Laplacian smoothing gradient descent

Download PDF
26 pages

Loading next page...
 
/lp/springer-journals/laplacian-smoothing-gradient-descent-ar7JxH0VZk
Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
eISSN
2197-9847
DOI
10.1007/s40687-022-00351-1
Publisher site
See Article on Publisher Site

Abstract

We propose a class of very simple modifications of gradient descent and stochastic gradient descent leveraging Laplacian smoothing. We show that when applied to a large variety of machine learning problems, ranging from logistic regression to deep neural nets, the proposed surrogates can dramatically reduce the variance, allow to take a larger step size, and improve the generalization accuracy. The methods only involve multiplying the usual (stochastic) gradient by the inverse of a positive definitive matrix (which can be computed efficiently by FFT) with a low condition number coming from a one-dimensional discrete Laplacian or its high-order generalizations. Given any vector, e.g., gradient vector, Laplacian smoothing preserves the mean and increases the smallest component and decreases the largest component. Moreover, we show that optimization algorithms with these surrogates converge uniformly in the discrete Sobolev Hσp\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$H_\sigma ^p$$\end{document} sense and reduce the optimality gap for convex optimization problems. The code is available at: https://github.com/BaoWangMath/LaplacianSmoothing-GradientDescent.

Journal

Research in the Mathematical Sciences – Springer Journals

Published: Sep 1, 2022

Keywords: Laplacian smoothing; Machine learning; Optimization

References

  • Katyusha: The first direct acceleration of stochastic gradient methods
    Allen-Zhu, Z
  • Optimization methods for large-scale machine learning
    Bottou, L; Curtis, EF; Nocedal, J
  • Adaptive subgradient methods for online learning and stochastic optimization
    Duchi, J; Hazan, E; Singer, Y
  • Gradient-based learning applied to document recognition
    LeCun, Y; Bottou, L; Bengio, Y; Haffner, P
  • Stochastic gradient descent as approximate bayesian inference
    Mandt, S; Hoffman, M; Blei, D
  • A method for solving the convex programming problem with convergence rate o(1/k2)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$o(1/k^2)$$\end{document}
    Nesterov, Y
  • On the momentum term in gradient descent learning algorithms
    Qian, N
  • A stochastic approximation method
    Robinds, H; Monro, S
  • Convergence analysis of gradient descent stochastic algorithms
    Shapiro, A; Wardi, Y
  • Mastering the game of go with deep neural networks and tree search
    Silver, D