FastAdaBelief: Improving Convergence Rate for Belief-based Adaptive Optimizers by Exploiting Strong Convexity (2021)
Attributed to:
Natural Language Generation for Low-resource Domains
funded by
EPSRC
Abstract
No abstract provided
Bibliographic Information
Digital Object Identifier: http://dx.doi.org/10.48550/arxiv.2104.13790
Publication URI: https://arxiv.org/abs/2104.13790
Type: Other