标题： 通用广义最小化算法 显示英文标题

标题： Universal Majorization-Minimization Algorithms

摘要： 主从最小化（MM）是一种优化方法的族类，它通过最小化一个局部紧密的上界（称为主函数）来迭代地减少损失。传统上，主函数是由人工推导的，而MM仅适用于少数经过深入研究的问题。我们提出了可以自动推导主函数的优化器，使用了最近广义泰勒模式自动微分的一种推广。这些通用MM优化器可以应用于任意问题，并且可以从任何起点收敛，无需调整超参数。 显示英文摘要

摘要： 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.