RSG: Beating Subgradient Method without Smoothness and Strong Convexity
This provides improved optimization algorithms for machine learning tasks such as regression and classification, though it is incremental as it builds on existing subgradient methods.
The paper tackles the inefficiency of the standard subgradient method in convex optimization by proposing a restarted subgradient (RSG) method, which achieves lower iteration complexity for finding ε-optimal solutions, with specific complexities like O(1/ε log(1/ε)) for problems with local quadratic growth.
In this paper, we study the efficiency of a {\bf R}estarted {\bf S}ub{\bf G}radient (RSG) method that periodically restarts the standard subgradient method (SG). We show that, when applied to a broad class of convex optimization problems, RSG method can find an $ε$-optimal solution with a lower complexity than the SG method. In particular, we first show that RSG can reduce the dependence of SG's iteration complexity on the distance between the initial solution and the optimal set to that between the $ε$-level set and the optimal set {multiplied by a logarithmic factor}. Moreover, we show the advantages of RSG over SG in solving three different families of convex optimization problems. (a) For the problems whose epigraph is a polyhedron, RSG is shown to converge linearly. (b) For the problems with local quadratic growth property in the $ε$-sublevel set, RSG has an $O(\frac{1}ε\log(\frac{1}ε))$ iteration complexity. (c) For the problems that admit a local Kurdyka-Łojasiewicz property with a power constant of $β\in[0,1)$, RSG has an $O(\frac{1}{ε^{2β}}\log(\frac{1}ε))$ iteration complexity. The novelty of our analysis lies at exploiting the lower bound of the first-order optimality residual at the $ε$-level set. It is this novelty that allows us to explore the local properties of functions (e.g., local quadratic growth property, local Kurdyka-Łojasiewicz property, more generally local error bound conditions) to develop the improved convergence of RSG. { We also develop a practical variant of RSG enjoying faster convergence than the SG method, which can be run without knowing the involved parameters in the local error bound condition.} We demonstrate the effectiveness of the proposed algorithms on several machine learning tasks including regression, classification and matrix completion.