Convergence of the Chambolle-Pock Algorithm in the Absence of Monotonicity
This work addresses convergence guarantees for a popular optimization algorithm in nonmonotone settings, which is incremental as it extends existing analysis to broader operator classes.
The paper tackles the convergence analysis of the Chambolle-Pock algorithm for problems lacking monotonicity, introducing new stepsize and relaxation parameter ranges that depend on singular values and extending results to semimonotone operators, with tightness demonstrated through examples.
The Chambolle-Pock algorithm (CPA), also known as the primal-dual hybrid gradient method, has gained popularity over the last decade due to its success in solving large-scale convex structured problems. This work extends its convergence analysis for problems with varying degrees of (non)monotonicity, quantified through a so-called oblique weak Minty condition on the associated primal-dual operator. Our results reveal novel stepsize and relaxation parameter ranges which do not only depend on the norm of the linear mapping, but also on its other singular values. In particular, in nonmonotone settings, in addition to the classical stepsize conditions, extra bounds on the stepsizes and relaxation parameters are required. On the other hand, in the strongly monotone setting, the relaxation parameter is allowed to exceed the classical upper bound of two. Moreover, we build upon the recently introduced class of semimonotone operators, providing sufficient convergence conditions for CPA when the individual operators are semimonotone. Since this class of operators encompasses traditional operator classes including (hypo)- and co(hypo)-monotone operators, this analysis recovers and extends existing results for CPA. Tightness of the proposed stepsize ranges is demonstrated through several examples.