Search Results for author: Himanshu Tyagi

Found 13 papers, 1 papers with code

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

no code implementations11 Sep 2021 Shubham K Jha, Prathamesh Mayekar, Himanshu Tyagi

We show that a simple scaled transmission analog coding scheme results in a slowdown in convergence rate by a factor of $\sqrt{d(1+1/\mathtt{SNR})}$.

Multiple Support Recovery Using Very Few Measurements Per Sample

no code implementations20 May 2021 Lekshmi Ramesh, Chandra R. Murthy, Himanshu Tyagi

For a given budget of $m$ measurements per sample, the goal is to recover the $\ell$ underlying supports, in the absence of the knowledge of group labels.

Wyner-Ziv Estimators: Efficient Distributed Mean Estimation with Side Information

no code implementations24 Nov 2020 Prathamesh Mayekar, Ananda Theertha Suresh, Himanshu Tyagi

Communication efficient distributed mean estimation is an important primitive that arises in many distributed learning and optimization scenarios such as federated learning.

Federated Learning

Unified lower bounds for interactive high-dimensional estimation under information constraints

no code implementations13 Oct 2020 Jayadev Acharya, Clément L. Canonne, Ziteng Sun, Himanshu Tyagi

We consider the task of distributed parameter estimation using interactive protocols subject to local information constraints such as bandwidth limitations, local differential privacy, and restricted measurements.

Interactive Inference under Information Constraints

no code implementations21 Jul 2020 Jayadev Acharya, Clément L. Canonne, Yu-Han Liu, Ziteng Sun, Himanshu Tyagi

We study the role of interactivity in distributed statistical inference under information constraints, e. g., communication constraints and local differential privacy.

Density Estimation

How Reliable are Test Numbers for Revealing the COVID-19 Ground Truth and Applying Interventions?

1 code implementation24 Apr 2020 Aditya Gopalan, Himanshu Tyagi

We use the simulation framework to compare the performance of three testing policies: Random Symptomatic Testing (RST), Contact Tracing (CT), and a new Location Based Testing policy (LBT).

RATQ: A Universal Fixed-Length Quantizer for Stochastic Optimization

no code implementations22 Aug 2019 Prathamesh Mayekar, Himanshu Tyagi

Finally, we propose an adaptive quantizer for gain which when used with RATQ for shape quantizer outperforms uniform gain quantization and is, in fact, close to optimal.

Quantization Stochastic Optimization

Domain Compression and its Application to Randomness-Optimal Distributed Goodness-of-Fit

no code implementations20 Jul 2019 Jayadev Acharya, Clément L. Canonne, Yanjun Han, Ziteng Sun, Himanshu Tyagi

We study goodness-of-fit of discrete distributions in the distributed setting, where samples are divided between multiple users who can only release a limited amount of information about their samples due to various information constraints.

Inference under Information Constraints II: Communication Constraints and Shared Randomness

no code implementations20 May 2019 Jayadev Acharya, Clément L. Canonne, Himanshu Tyagi

We propose a general-purpose simulate-and-infer strategy that uses only private-coin communication protocols and is sample-optimal for distribution learning.

Inference under Information Constraints I: Lower Bounds from Chi-Square Contraction

no code implementations30 Dec 2018 Jayadev Acharya, Clément L. Canonne, Himanshu Tyagi

Underlying our bounds is a characterization of the contraction in chi-square distances between the observed distributions of the samples when information constraints are placed.

Test without Trust: Optimal Locally Private Distribution Testing

no code implementations7 Aug 2018 Jayadev Acharya, Clément L. Canonne, Cody Freitag, Himanshu Tyagi

We are concerned with two settings: First, when we insist on using an already deployed, general-purpose locally differentially private mechanism such as the popular RAPPOR or the recently introduced Hadamard Response for collecting data, and must build our tests based on the data collected via this mechanism; and second, when no such restriction is imposed, and we can design a bespoke mechanism specifically for testing.

Distributed Simulation and Distributed Inference

no code implementations19 Apr 2018 Jayadev Acharya, Clément L. Canonne, Himanshu Tyagi

Nonetheless, we present a Las Vegas algorithm that simulates a single sample from the unknown distribution using $O(k/2^\ell)$ samples in expectation.

Estimating Renyi Entropy of Discrete Distributions

no code implementations2 Aug 2014 Jayadev Acharya, Alon Orlitsky, Ananda Theertha Suresh, Himanshu Tyagi

It was recently shown that estimating the Shannon entropy $H({\rm p})$ of a discrete $k$-symbol distribution ${\rm p}$ requires $\Theta(k/\log k)$ samples, a number that grows near-linearly in the support size.

Cannot find the paper you are looking for? You can Submit a new open access paper.