论文标题
Tadam：强大的随机梯度优化器
TAdam: A Robust Stochastic Gradient Optimizer
论文作者
论文摘要
机器学习算法旨在从观测值中找到模式，其中可能包括一些噪声，尤其是在机器人域中。即使有这样的噪音，我们也希望他们能够在需要时检测到异常值并丢弃它们。因此，我们提出了一种新的随机梯度优化方法，其鲁棒性是在算法中直接构建的，使用稳健的学生-T分布作为其核心思想。受欢迎的优化方法亚当通过我们的方法进行了修改，结果优化器，所谓的tadam，被证明可以有效地超过亚当的鲁棒性，以抵抗多样化的任务，从回归和分类到加强学习问题。可以在https://github.com/mahoumaru/tadam.git上找到我们算法的实现
Machine learning algorithms aim to find patterns from observations, which may include some noise, especially in robotics domain. To perform well even with such noise, we expect them to be able to detect outliers and discard them when needed. We therefore propose a new stochastic gradient optimization method, whose robustness is directly built in the algorithm, using the robust student-t distribution as its core idea. Adam, the popular optimization method, is modified with our method and the resultant optimizer, so-called TAdam, is shown to effectively outperform Adam in terms of robustness against noise on diverse task, ranging from regression and classification to reinforcement learning problems. The implementation of our algorithm can be found at https://github.com/Mahoumaru/TAdam.git
