Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence

Abstract

Difference of convex (DC) functions cover a broad family of non-convex and possibly non-smooth and non-differentiable functions, and have wide applications in machine learning and statistics. Although deterministic algorithms for DC functions have been extensively studied, stochastic optimization that is more suitable for learning with big data remains under-explored. In this paper, we propose new stochastic optimization algorithms and study their first-order convergence theories for solving a broad family of DC functions. We improve the existing algorithms and theories of stochastic optimization for DC functions from both practical and theoretical perspectives. On the practical side, our algorithm is more user-friendly without requiring a large mini-batch size and more efficient by saving unnecessary computations. On the theoretical side, our convergence analysis does not necessarily require the involved functions to be smooth with Lipschitz continuous gradient. Instead, the convergence rate of the proposed stochastic algorithm is automatically adaptive to the Hölder continuity of the gradient of one component function. Moreover, we extend the proposed stochastic algorithms for DC functions to solve problems with a general non-convex non-differentiable regularizer, which does not necessarily have a DC decomposition but enjoys an efficient proximal mapping. To the best of our knowledge, this is the first work that gives the first non-asymptotic convergence for solving non-convex optimization whose objective has a general non-convex non-differentiable regularizer.

arXiv commentIn the revised version, we present some improved complexity results for non-smooth and non-convex regularizers and for functions with known Hölder continuity parameter $\nu \in (0,1]$ by a simple change of an algorithmic parameter

References in corpus (9)

• Nearly unbiased variable selection under minimax concave penalty
• A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems
• Douglas-Rachford splitting for nonconvex optimization with application to nonconvex feasibility problems
• Positive-Unlabeled Learning with Non-Negative Risk Estimator
• Stochastic subgradient method converges at the rate $O(k^{-1/4})$ on weakly convex functions
• Convergence guarantees for a class of non-convex and non-smooth optimization problems
• On the Convergence Rate of Stochastic Mirror Descent for Nonsmooth Nonconvex Optimization
• Learning with Non-Convex Truncated Losses by SGD
• Proximal Gradient Method with Extrapolation and Line Search for a Class of Nonconvex and Nonsmooth Problems