Corpus ID: 219573286

A General Framework for Analyzing Stochastic Dynamics in Learning Algorithms

@article{Chou2020AGF,
  title={A General Framework for Analyzing Stochastic Dynamics in Learning Algorithms},
  author={Chi-Ning Chou and Mien Brabeeba Wang and Tiancheng Yu},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.06171}
}
  • Chi-Ning Chou, Mien Brabeeba Wang, Tiancheng Yu
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • We present a general framework for analyzing high-probability bounds for stochastic dynamics in learning algorithms. Our framework composes standard techniques such as a stopping time, a martingale concentration and a closed-from solution to give a streamlined three-step recipe with a general and flexible principle to implement it. To demonstrate the power and the flexibility of our framework, we apply the framework on three very different learning problems: stochastic gradient descent for… CONTINUE READING

    Tables and Topics from this paper.