On the Convergence Rate of Stochastic Mirror Descent for Nonsmooth Nonconvex Optimization

In this paper, we investigate the non-asymptotic stationary convergence behavior of Stochastic Mirror Descent (SMD) for nonconvex optimization. We focus on a general class of nonconvex nonsmooth stochastic optimization problems, in which the objective can be decomposed into a relatively weakly convex function (possibly non-Lipschitz) and a simple non-smooth convex regularizer. We prove that SMD, without the use of mini-batch, is guaranteed to converge to a stationary point in a convergence rate of $ \mathcal{O}(1/\sqrt{t}) $. The efficiency estimate matches with existing results for stochastic subgradient method, but is evaluated under a stronger stationarity measure. Our convergence analysis applies to both the original SMD and its proximal version, as well as the deterministic variants, for solving relatively weakly convex problems.

[1]  John Darzentas,et al.  Problem Complexity and Method Efficiency in Optimization , 1983 .

[2]  Jean-Philippe Vial,et al.  Strong and Weak Convexity of Sets and Functions , 1983, Math. Oper. Res..

[3]  Heinz H. Bauschke,et al.  Joint minimization with alternating Bregman proximity operators , 2005 .

[4]  Jieping Ye,et al.  Large-scale sparse logistic regression , 2009, KDD.

[5]  Alexander Shapiro,et al.  Stochastic Approximation approach to Stochastic Programming , 2013 .

[6]  Ambuj Tewari,et al.  Composite objective mirror descent , 2010, COLT 2010.

[7]  Saeed Ghadimi,et al.  Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming , 2013, SIAM J. Optim..

[8]  Yuantao Gu,et al.  The Convergence Guarantees of a Non-Convex Approach for Sparse Recovery , 2012, IEEE Transactions on Signal Processing.

[9]  Niao He Saddle point techniques in convex composite and error-in-measurement optimization , 2015 .

[10]  Saeed Ghadimi,et al.  Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization , 2013, Mathematical Programming.

[11]  Stephen P. Boyd,et al.  Stochastic Mirror Descent in Variationally Coherent Optimization Problems , 2017, NIPS.

[12]  Damek Davis,et al.  The nonsmooth landscape of phase retrieval , 2017, IMA Journal of Numerical Analysis.

[13]  D. Drusvyatskiy The proximal point method revisited , 2017, 1712.06038.

[14]  Yuantao Gu,et al.  Nonconvex Sparse Logistic Regression With Weakly Convex Regularization , 2017, IEEE Transactions on Signal Processing.

[15]  Yurii Nesterov,et al.  Relatively Smooth Convex Optimization by First-Order Methods, and Applications , 2016, SIAM J. Optim..

[16]  Dmitriy Drusvyatskiy,et al.  Stochastic subgradient method converges at the rate O(k-1/4) on weakly convex functions , 2018, ArXiv.

[17]  Damek Davis,et al.  Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems , 2017, SIAM J. Optim..

[18]  Haihao Lu “Relative Continuity” for Non-Lipschitz Nonsmooth Convex Optimization Using Stochastic (or Deterministic) Mirror Descent , 2017, INFORMS Journal on Optimization.