activity
20182025
most citedInformation-constrained optimization: can adaptive processing of gradients help?

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2019

RATQ: A Universal Fixed-Length Quantizer for Stochastic Optimization

Prathamesh Mayekar, Himanshu Tyagi

We present Rotated Adaptive Tetra-iterated Quantizer (RATQ), a fixed-length quantizer for gradients in first order stochastic optimization. RATQ is easy to implement and involves o…