Patents by Inventor John Duchi

John Duchi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • User behavior model development with private federated learning
    Patent number: 12052315
    Abstract: Embodiments described herein provide for a non-transitory machine-readable medium storing instructions to cause one or more processors to receive, at a client device, a machine learning model from a server, detect a usage pattern for a content item, store an association between the content item and the detected usage pattern in local data, train the machine learning model using local data for the content item with the detected usage pattern to generate a trained machine learning model, generate an update for the machine learning model, privatize the update for the machine learning model, and transmit the privatized update for the machine learning model to the server.
    Type: Grant
    Filed: December 21, 2020
    Date of Patent: July 30, 2024
    Assignee: Apple Inc.
    Inventors: Stephen Cosman, Kalu Onuka Kalu, Marcelo Lotif Araujo, Michael Chatzidakis, Thi Hai Van Do, Alexis Hugo Louis Durocher, Guillaume Tartavel, Sowmya Gopalan, Vignesh Jagadeesh, Abhishek Bhowmick, John Duchi, Julien Freudiger, Gaurav Kapoor, Ryan M. Rogers
  • Private federated learning with protection against reconstruction
    Patent number: 11989634
    Abstract: Embodiments described herein provide for a non-transitory machine-readable medium storing instructions to cause one or more processors to perform operations comprising receiving a machine learning model from a server at a client device, training the machine learning model using local data at the client device, generating an update for the machine learning model, the update including a weight vector that represents a difference between the received machine learning model and the trained machine learning model, privatizing the update for the machine learning model, and transmitting the privatized update for the machine learning model to the server.
    Type: Grant
    Filed: January 17, 2020
    Date of Patent: May 21, 2024
    Assignee: Apple Inc.
    Inventors: Abhishek Bhowmick, John Duchi, Julien Freudiger, Gaurav Kapoor, Ryan M. Rogers
  • USER BEHAVIOR MODEL DEVELOPMENT WITH PRIVATE FEDERATED LEARNING
    Publication number: 20210192078
    Abstract: Embodiments described herein provide for a non-transitory machine-readable medium storing instructions to cause one or more processors to receive, at a client device, a machine learning model from a server, detect a usage pattern for a content item, store an association between the content item and the detected usage pattern in local data, train the machine learning model using local data for the content item with the detected usage pattern to generate a trained machine learning model, generate an update for the machine learning model, privatize the update for the machine learning model, and transmit the privatized update for the machine learning model to the server.
    Type: Application
    Filed: December 21, 2020
    Publication date: June 24, 2021
    Inventors: Stephen Cosman, Kalu Onuka Kalu, Marcelo Lotif Araujo, Michael Chatzidakis, Thi Hai Van Do, Alexis Hugo Louis Durocher, Guillaume Tartavel, Sowmya Gopalan, Vignesh Jagadeesh, Abhishek Bhowmick, John Duchi, Julien Freudiger, Gaurav Kapoor, Ryan M. Rogers
  • PRIVATE FEDERATED LEARNING WITH PROTECTION AGAINST RECONSTRUCTION
    Publication number: 20210166157
    Abstract: Embodiments described herein provide for a non-transitory machine-readable medium storing instructions to cause one or more processors to perform operations comprising receiving a machine learning model from a server at a client device, training the machine learning model using local data at the client device, generating an update for the machine learning model, the update including a weight vector that represents a difference between the received machine learning model and the trained machine learning model, privatizing the update for the machine learning model, and transmitting the privatized update for the machine learning model to the server.
    Type: Application
    Filed: January 17, 2020
    Publication date: June 3, 2021
    Inventors: Abhishek Bhowmick, John Duchi, Julien Freudiger, Gaurav Kapoor, Ryan M. Rogers