论文信息 - Smooth minimization of non-smooth functions

Smooth minimization of non-smooth functions

Abstract.In this paper we propose a new approach for constructing efficient schemes for non-smooth convex optimization. It is based on a special smoothing technique, which can be applied to functions with explicit max-structure. Our approach can be considered as an alternative to black-box minimization. From the viewpoint of efficiency estimates, we manage to improve the traditional bounds on the number of iterations of the gradient schemes from keeping basically the complexity of each iteration unchanged.

Yurii Nesterov | Y. Nesterov

[1] Jean-Louis Goffin,et al. On convergence rates of subgradient optimization methods , 1977, Math. Program..

[2] B. T. Poljak. On the Bertsekas' method for minimization of composite functions , 1979 .

[3] Dimitri P. Bertsekas,et al. Constrained Optimization and Lagrange Multiplier Methods , 1982 .

[4] Y. Nesterov. A method for unconstrained convex minimization problem with the rate of convergence o(1/k^2) , 1983 .

[5] Christian,et al. The Author Would like to Thank , 1988 .

[6] J. Hiriart-Urruty,et al. Convex analysis and minimization algorithms , 1993 .

[7] O. Nelles,et al. An Introduction to Optimization , 1996, IEEE Antennas and Propagation Magazine.

[8] Arkadi Nemirovski,et al. Lectures on modern convex optimization - analysis, algorithms, and engineering applications , 2001, MPS-SIAM series on optimization.

[9] Roman A. Polyak,et al. Nonlinear rescaling vs. smoothing technique in convex optimization , 2002, Math. Program..

[10] Yurii Nesterov,et al. Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.