Optimizing ADMM and Over-Relaxed ADMM Parameters for Linear Quadratic Problems
This work addresses parameter selection challenges for ADMM in machine learning, offering incremental improvements for specific linear quadratic problems.
The paper tackles the problem of optimizing penalty and relaxation parameters for ADMM and over-relaxed ADMM in linear quadratic problems, proposing a general approach for penalty parameter optimization and a novel closed-form formula for relaxation parameter, validated through experiments on random instantiations and imaging applications.
The Alternating Direction Method of Multipliers (ADMM) has gained significant attention across a broad spectrum of machine learning applications. Incorporating the over-relaxation technique shows potential for enhancing the convergence rate of ADMM. However, determining optimal algorithmic parameters, including both the associated penalty and relaxation parameters, often relies on empirical approaches tailored to specific problem domains and contextual scenarios. Incorrect parameter selection can significantly hinder ADMM's convergence rate. To address this challenge, in this paper we first propose a general approach to optimize the value of penalty parameter, followed by a novel closed-form formula to compute the optimal relaxation parameter in the context of linear quadratic problems (LQPs). We then experimentally validate our parameter selection methods through random instantiations and diverse imaging applications, encompassing diffeomorphic image registration, image deblurring, and MRI reconstruction.