Journal of Optimization Theory and Applications Исследование операций и наука управления
Monotone and Nonmonotone Linearized Block Coordinate Descent Methods for Nonsmooth Composite Optimization Problems
Аннотация
Abstract In this paper, we introduce both monotone and nonmonotone variants of LiBCoD, a Li nearized B lock Co ordinate D escent method for solving composite optimization problems. At each iteration, a random block is selected, and the smooth components of the objective are linearized along the chosen block in a Gauss-Newton approach. For the monotone variant, we establish a global sublinear convergence rate to a stationary point under the assumption of bounded iterates. For the nonmonotone variant, we derive a global sublinear convergence rate without requiring global Lipschitz continuity or bounded iterates. Preliminary numerical experiments highlight the promising performance of the proposed approach.