First-order methods almost always avoid strict saddle points

This publication has 31 references indexed in Scilit:

• Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
  Mathematical Programming, 2012
• Random Matrices and Complexity of Spin Glasses
  Communications on Pure and Applied Mathematics, 2012
• Projection-like Retractions on Matrix Manifolds
  SIAM Journal on Optimization, 2012
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward–backward splitting, and regularized Gauss–Seidel methods
  Mathematical Programming, 2011
• Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
  Transactions of the American Mathematical Society, 2009
• Cubic regularization of Newton method and its global performance
  Mathematical Programming, 2006
• Convergence of the Iterates of Descent Methods for Analytic Cost Functions
  SIAM Journal on Optimization, 2005
• Nonconvergence to Unstable Points in Urn Models and Stochastic Approximations
  The Annals of Probability, 1990
• On the use of directions of negative curvature in a modified newton method
  Mathematical Programming, 1979
• Newton-type methods for unconstrained and linearly constrained optimization
  Mathematical Programming, 1974