Linear convergence of first order methods for non-strongly convex optimization
- 574 Downloads
The standard assumption for proving linear convergence of first order methods for smooth convex optimization is the strong convexity of the objective function, an assumption which does not hold for many practical applications. In this paper, we derive linear convergence rates of several first order methods for solving smooth non-strongly convex constrained optimization problems, i.e. involving an objective function with a Lipschitz continuous gradient that satisfies some relaxed strong convexity condition. In particular, in the case of smooth constrained convex optimization, we provide several relaxations of the strong convexity conditions and prove that they are sufficient for getting linear convergence for several first order methods such as projected gradient, fast gradient and feasible descent methods. We also provide examples of functional classes that satisfy our proposed relaxations of strong convexity conditions. Finally, we show that the proposed relaxed strong convexity conditions cover important applications ranging from solving linear systems, Linear Programming, and dual formulations of linearly constrained convex problems.
Mathematics Subject Classification90C25 90C06 65K05
The research leading to these results has received funding from the Executive Agency for Higher Education, Research and Innovation Funding (UEFISCDI), Romania: PN-III-P4-PCE-2016-0731, project ScaleFreeNet, No. 39/2017.
- 7.Lewis, A.S., Pang, J.S.: Error bounds for convex inequality systems. In: Chapter In: Generalized Convexity, Generalized Monotonicity–Recent Results. Springer, Berlin (1998)Google Scholar
- 8.Yangy, T., Lin, Q.: A stochastic gradient method with linear convergence rate for a class of non-smooth non-strongly convex optimization. Tech. rep. (2015). www.arxiv.org
- 14.Drusvyatskiy, D., Lewis, A.: Error bounds, quadratic growth, and linear convergence of proximal methods. Tech. rep., (2016). (arXiv:1602.06661)
- 22.Lin, H., Mairal, J., Harchaoui, Z.: A universal Catalyst for first-order optimization. In: Advances in neural information processing systems, 3384–3392 (2015)Google Scholar