Generalized Uniformly Optimal Methods for Nonlinear Programming

Abstract

In this paper, we present a generic framework to extend existing uniformly optimal convex programming algorithms to solve more general nonlinear, possibly nonconvex, optimization problems. The basic idea is to incorporate a local search step (gradient descent or Quasi-Newton iteration) into these uniformly optimal convex programming methods, and then enforce a monotone decreasing property of the function values computed along the trajectory. Algorithms of these types will then achieve the best known complexity for nonconvex problems, and the optimal complexity for convex ones without requiring any problem parameters. As a consequence, we can have a unified treatment for a general class of nonlinear programming problems regardless of their convexity and smoothness level. In particular, we show that the accelerated gradient and level methods, both originally designed for solving convex optimization problems only, can be used for solving both convex and nonconvex problems uniformly. In a similar vein, we show that some well-studied techniques for nonlinear programming, e.g., Quasi-Newton iteration, can be embedded into optimal convex optimization algorithms to possibly further enhance their numerical performance. Our theoretical and algorithmic developments are complemented by some promising numerical results obtained for solving a few important nonconvex and nonlinear data analysis problems in the literature.

Cited by in corpus (7)

• Theoretical properties of the global optimizer of two layer neural network
• Catalyst Acceleration for Gradient-Based Non-Convex Optimization
• A Doubly Accelerated Inexact Proximal Point Method for Nonconvex Composite Optimization Problems
• Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs
• Accelerated Stochastic Algorithms for Nonconvex Finite-sum and Multi-block Optimization
• An Inexact Variable Metric Proximal Point Algorithm for Generic Quasi-Newton Acceleration
• Accelerated first-order methods for large-scale convex minimization