arXiv Open Access 2021

$\bar{G}_{mst}$:An Unbiased Stratified Statistic and a Fast Gradient Optimization Algorithm Based on It

Aixiang Chen
Lihat Sumber

Abstrak

-The fluctuation effect of gradient expectation and variance caused by parameter update between consecutive iterations is neglected or confusing by current mainstream gradient optimization algorithms. The work in this paper remedy this issue by introducing a novel unbiased stratified statistic \ $\bar{G}_{mst}$\ , a sufficient condition of fast convergence for \ $\bar{G}_{mst}$\ also is established. A novel algorithm named MSSG designed based on \ $\bar{G}_{mst}$\ outperforms other sgd-like algorithms. Theoretical conclusions and experimental evidence strongly suggest to employ MSSG when training deep model.

Topik & Kata Kunci

Penulis (1)

A

Aixiang Chen

Format Sitasi

Chen, A. (2021). $\bar{G}_{mst}$:An Unbiased Stratified Statistic and a Fast Gradient Optimization Algorithm Based on It. https://arxiv.org/abs/2110.03354

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓