A Deterministic Gradient-Based Approach to Avoid Saddle Points

Lisa Maria Kreusser, Stanley J. Osher, Bao Wang

Research output: Contribution to journalArticlepeer-review

2 Downloads (Pure)


Loss functions with a large number of saddle points are one of the major obstacles for training modern machine learning models efficiently. First-order methods such as gradient descent are usually the methods of choice for training machine learning models. However, these methods converge to saddle points for certain choices of initial guesses. In this paper, we propose a modification of the recently proposed Laplacian smoothing gradient descent [Osher et al., arXiv:1806.06317], called modified Laplacian smoothing gradient descent (mLSGD), and demonstrate its potential to avoid saddle points without sacrificing the convergence rate. Our analysis is based on the attraction region, formed by all starting points for which the considered numerical scheme converges to a saddle point. We investigate the attraction region's dimension both analytically and numerically. For a canonical class of quadratic functions, we show that the dimension of the attraction region for mLSGD is floor((n-1)/2), and hence it is significantly smaller than that of the gradient descent whose dimension is n-1.
Original languageEnglish
Pages (from-to)1-20
Number of pages20
JournalEuropean Journal of Applied Mathematics
Early online date9 Nov 2022
Publication statusE-pub ahead of print - 9 Nov 2022


  • cs.LG
  • cs.NA
  • math.DS
  • math.NA
  • stat.ML


Dive into the research topics of 'A Deterministic Gradient-Based Approach to Avoid Saddle Points'. Together they form a unique fingerprint.

Cite this