English

DTN: A Learning Rate Scheme with Convergence Rate of $\mathcal{O}(1/t)$ for SGD

Machine Learning 2019-03-01 v3 Optimization and Control Machine Learning

Abstract

This paper has some inconsistent results, i.e., we made some failed claims because we did some mistakes for using the test criterion for a series. Precisely, our claims on the convergence rate of O(1/t)\mathcal{O}(1/t) of SGD presented in Theorem 1, Corollary 1, Theorem 2 and Corollary 2 are wrongly derived because they are based on Lemma 5. In Lemma 5, we do not correctly use the test criterion for a series. Hence, the result of Lemma 5 is not valid. We would like to thank the community for pointing out this mistake!

Keywords

Cite

@article{arxiv.1901.07634,
  title  = {DTN: A Learning Rate Scheme with Convergence Rate of $\mathcal{O}(1/t)$ for SGD},
  author = {Lam M. Nguyen and Phuong Ha Nguyen and Dzung T. Phan and Jayant R. Kalagnanam and Marten van Dijk},
  journal= {arXiv preprint arXiv:1901.07634},
  year   = {2019}
}

Comments

This paper has inconsistent results, i.e., we made some failed claims because we did some mistakes for using the test criterion for a series