RATQ: A Universal Fixed-Length Quantizer for Stochastic Optimization

DOI10.1109/TIT.2021.3058663zbMath1473.90098arXiv1908.08200OpenAlexW3037740066MaRDI QIDQ5001606

Prathamesh Mayekar, Himanshu Tyagi

Publication date: 22 July 2021

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.08200

zbMATH Keywords

fixed-length quantizer for gradients in first order stochastic optimizationRotated Adaptive Tetra-iterated Quantizer (RATQ)

Mathematics Subject Classification ID

Derivative-free methods and methods using generalized derivatives (90C56) Stochastic programming (90C15) Coding theorems (Shannon theory) (94A24)

This page was built for publication: RATQ: A Universal Fixed-Length Quantizer for Stochastic Optimization