English

Stochastic gradient descent algorithms for strongly convex functions at O(1/T) convergence rates

Machine Learning 2013-05-13 v1 Artificial Intelligence

Abstract

With a weighting scheme proportional to t, a traditional stochastic gradient descent (SGD) algorithm achieves a high probability convergence rate of O({\kappa}/T) for strongly convex functions, instead of O({\kappa} ln(T)/T). We also prove that an accelerated SGD algorithm also achieves a rate of O({\kappa}/T).

Keywords

Cite

@article{arxiv.1305.2218,
  title  = {Stochastic gradient descent algorithms for strongly convex functions at O(1/T) convergence rates},
  author = {Shenghuo Zhu},
  journal= {arXiv preprint arXiv:1305.2218},
  year   = {2013}
}