Boundary Conditions for Linear Exit Time Gradient Trajectories Around Saddle Points: Analysis and Algorithm

by   Rishabh Dixit, et al.

Gradient-related first-order methods have become the workhorse of large-scale numerical optimization problems. Many of these problems involve nonconvex objective functions with multiple saddle points, which necessitates an understanding of the behavior of discrete trajectories of first-order methods within the geometrical landscape of these functions. This paper concerns convergence of first-order discrete methods to a local minimum of nonconvex optimization problems that comprise strict saddle points within the geometrical landscape. To this end, it focuses on analysis of discrete gradient trajectories around saddle neighborhoods, derives sufficient conditions under which these trajectories can escape strict-saddle neighborhoods in linear time, explores the contractive and expansive dynamics of these trajectories in neighborhoods of strict-saddle points that are characterized by gradients of moderate magnitude, characterizes the non-curving nature of these trajectories, and highlights the inability of these trajectories to re-enter the neighborhoods around strict-saddle points after exiting them. Based on these insights and analyses, the paper then proposes a simple variant of the vanilla gradient descent algorithm, termed Curvature Conditioned Regularized Gradient Descent (CCRGD) algorithm, which utilizes a check for an initial boundary condition to ensure its trajectories can escape strict-saddle neighborhoods in linear time. Convergence analysis of the CCRGD algorithm, which includes its rate of convergence to a local minimum within a geometrical landscape that has a maximum number of strict-saddle points, is also presented in the paper. Numerical experiments are then provided on a test function as well as a low-rank matrix factorization problem to evaluate the efficacy of the proposed algorithm.


page 1

page 2

page 3

page 4


Exit Time Analysis for Approximations of Gradient Descent Trajectories Around Saddle Points

This paper considers the problem of understanding the exit time for traj...

Accelerated gradient methods for nonconvex optimization: Escape trajectories from strict saddle points and convergence to local minima

This paper considers the problem of understanding the behavior of a gene...

Local and Global Convergence of General Burer-Monteiro Tensor Optimizations

Tensor optimization is crucial to massive machine learning and signal pr...

The Landscape of Matrix Factorization Revisited

We revisit the landscape of the simple matrix factorization problem. For...

Analysis of Asymptotic Escape of Strict Saddle Sets in Manifold Optimization

In this paper, we provide some analysis on the asymptotic escape of stri...

Over-parametrization via Lifting for Low-rank Matrix Sensing: Conversion of Spurious Solutions to Strict Saddle Points

This paper studies the role of over-parametrization in solving non-conve...

Escaping strict saddle points of the Moreau envelope in nonsmooth optimization

Recent work has shown that stochastically perturbed gradient methods can...

Please sign up or login with your details

Forgot password? Click here to reset