The mathematics of machine learning and deep learning - Sanjeev Arora (USA)——ICM2018的一小时报告
发文时间：2018-09-28
来源：304am永利集团
Abstract: Machine learning is the sub-field of computer science concerned with creating programs and machines that can improve from experience and interaction. It relies upon mathematical optimization, statistics, and algorithm design. The talk will be an introduction to machine learning, and to its popular subarea, deep learning. Empirical success here currently outstrips mathematical understanding. We will survey some of the myriad mathematical mysteries of this field, and initial progress made towards understanding them.
https://eta.impa.br/dl/PL019.pdf
本文讨论机器学习中的数学最优化。首先是梯度下降和凸优化。对于非凸模型，作者介绍了深度网的方法。寻找最优深度网涉及计算复杂性和统计复杂性问题。作者研究了无人监督的学习中的数学模型。最后讨论强化学习， 其数学模型是Markov决策过程。
相关附件
15-PL019 Arora
