activity
20182021
most citedInformation-constrained optimization: can adaptive processing of gradients help?

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

collaborators

5 papers

cs.IT2021

Fundamental limits of over-the-air optimization: Are analog schemes optimal?

Shubham K Jha, Prathamesh Mayekar, Himanshu Tyagi

We consider over-the-air convex optimization on a dimensional space where coded gradients are sent over an additive Gaussian noise channel with variance . The codewords sa…

math.OC20211 cited

Information-constrained optimization: can adaptive processing of gradients help?

Jayadev Acharya, Clément L. Canonne, Prathamesh Mayekar +1

We revisit first-order optimization under local information constraints such as local privacy, gradient quantization, and computational constraints limiting access to a few coordin…

cs.IT2020

Limits on Gradient Compression for Stochastic Optimization

Prathamesh Mayekar, Himanshu Tyagi

We consider stochastic optimization over spaces using access to a first-order oracle. We ask: {What is the minimum precision required for oracle outputs to retain the unre…

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…

cs.IT2018

Optimal Source Codes for Timely Updates

Prathamesh Mayekar, Parimal Parag, Himanshu Tyagi

A transmitter observing a sequence of independent and identically distributed random variables seeks to keep a receiver updated about its latest observations. The receiver need not…