Time-Variation in Online Nonconvex Optimization Enables Escaping From Spurious Local Minima

• 成果类型: Article
• 署名作者: Ding, Yuhao; Lavaei, Javad; Arcak, Murat
• 署名单位: University of California System; University of California Berkeley; University of California System; University of California Berkeley
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2021.3135361
• 发表日期: 2023
• 页码: 156-171
• 关键词: Nonconvex optimization; stability analysis; time-varying optimization

摘要

A major limitation of online algorithms that track the optimizers of time-varying nonconvex optimization problems is that they focus on a specific local minimum trajectory, which may lead to poor spurious local solutions. In this article, we show that the natural temporal variation may help simple online tracking methods find and track time-varying global minima. To this end, we investigate the properties of a time-varying projected gradient flow system with inertia, which can be regarded as the continuous-time limit of (1) the optimality conditions for a discretized sequential optimization problem with a proximal regularization and (2) the online tracking scheme. We introduce the notion of the dominant trajectory and show that the inherent temporal variation could reshape the landscape of the Lagrange functional and help a proximal algorithm escape the spurious local minimum trajectories if the global minimum trajectory is dominant. For a problem with twice continuously differentiable objective function and constraints, sufficient conditions are derived to guarantee that no matter how a local search method is initialized, it will track a time-varying global solution after some time. The results are illustrated on a benchmark example with many local minima.