Majorization-minimization (MM) is a family of optimization methods that iteratively reduce a loss by minimizing a locally-tight upper bound, called a majorizer. Traditionally, majorizers were derived by hand, and MM was only applicable to a small number of well-studied problems. We present optimizers that instead derive majorizers automatically, using a recent generalization of Taylor mode automatic differentiation. These universal MM optimizers can be applied to arbitrary problems and converge from any starting point, with no hyperparameter tuning.

翻译：主最小化（MM）是一类优化方法，通过迭代极小化称为主化函数的局部紧上界来降低损失。传统上，主化函数需手动推导，MM仅适用于少数经过充分研究的问题。我们提出的优化器利用泰勒模式自动微分的最新推广方法，自动推导主化函数。这些通用MM优化器可应用于任意问题，从任意初始点出发均能收敛，且无需超参数调优。