Log in
Enquire now
‌

US Patent 11785073 Systems and methods for communication efficient distributed mean estimation

Patent 11785073 was granted and assigned to Google on October, 2023 by the United States Patent and Trademark Office.

OverviewStructured DataIssuesContributors

Contents

Is a
Patent
Patent

Patent attributes

Patent Applicant
Google
Google
Current Assignee
Google
Google
Patent Jurisdiction
United States Patent and Trademark Office
United States Patent and Trademark Office
Patent Number
11785073
Patent Inventor Names
Ananda Theertha Suresh
Sanjiv Kumar
Xinnan Yu
Hugh Brendan McMahan
Date of Patent
October 10, 2023
Patent Application Number
17502794
Date Filed
October 15, 2021
Patent Citations
‌
US Patent 8954357 Multi-task machine learning using features bagging and local relatedness in the instance space
‌
US Patent 9190055 Named entity recognition with personalized models
‌
US Patent 9275398 Obtaining metrics for client-side display of content
‌
US Patent 9336483 Dynamically updated neural network structures for content distribution networks
‌
US Patent 9424836 Privacy-sensitive speech model creation via aggregation of multiple user models
‌
US Patent 9390370 Training deep neural network acoustic models using distributed hessian-free optimization
‌
US Patent 7664249 Methods and interfaces for probing and understanding behaviors of alerting and filtering systems based on models and simulation from logs
‌
US Patent 8018874 Network optimization system implementing distributed particle swarm optimization
...
Patent Primary Examiner
‌
Kevin W Figueroa
CPC Code
‌
H03M 7/40
‌
H03M 7/3082
‌
G06F 17/12
Patent abstract

The present disclosure provides systems and methods for communication efficient distributed mean estimation. In particular, aspects of the present disclosure can be implemented by a system in which a number of vectors reside on a number of different clients, and a centralized server device seeks to estimate the mean of such vectors. According to one aspect of the present disclosure, a client computing device can rotate a vector by a random rotation matrix and then subsequently perform probabilistic quantization on the rotated vector. According to another aspect of the present disclosure, subsequent to quantization but prior to transmission, the client computing can encode the quantized vector according to a variable length coding scheme (e.g., by computing variable length codes).

Timeline

No Timeline data yet.

Further Resources

Title
Author
Link
Type
Date
No Further Resources data yet.

References

Find more entities like US Patent 11785073 Systems and methods for communication efficient distributed mean estimation

Use the Golden Query Tool to find similar entities by any field in the Knowledge Graph, including industry, location, and more.
Open Query Tool
Access by API
Golden Query Tool
Golden logo

Company

  • Home
  • Press & Media
  • Blog
  • Careers
  • WE'RE HIRING

Products

  • Knowledge Graph
  • Query Tool
  • Data Requests
  • Knowledge Storage
  • API
  • Pricing
  • Enterprise
  • ChatGPT Plugin

Legal

  • Terms of Service
  • Enterprise Terms of Service
  • Privacy Policy

Help

  • Help center
  • API Documentation
  • Contact Us