Patents by Inventor Swaroop Indra Ramaswamy

Swaroop Indra Ramaswamy 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).

  • Publication number: 20250037707
    Abstract: Implementations disclosed herein are directed to federated learning of machine learning (“ML”) model(s) based on gradient(s) generated at corresponding client devices and a remote system. Processor(s) of the corresponding client devices can process client data generated locally at the corresponding client devices using corresponding on-device ML model(s) to generate corresponding predicted outputs, generate corresponding client gradients based on the corresponding predicted outputs, and transmit the corresponding client gradients to the remote system. Processor(s) of the remote system can process remote data obtained from remote database(s) using global ML model(s) to generate additional corresponding predicted outputs, generate corresponding remote gradients based on the additional corresponding predicted outputs. Further, the remote system can utilize the corresponding client gradients and the corresponding remote gradients to update the global ML model(s) or weights thereof.
    Type: Application
    Filed: October 16, 2024
    Publication date: January 30, 2025
    Inventors: Françoise Beaufays, Andrew Hard, Swaroop Indra Ramaswamy, Om Dipakbhai Thakkar, Rajiv Mathews
  • Patent number: 12205575
    Abstract: Implementations disclosed herein are directed to federated learning of machine learning (“ML”) model(s) based on gradient(s) generated at corresponding client devices and a remote system. Processor(s) of the corresponding client devices can process client data generated locally at the corresponding client devices using corresponding on-device ML model(s) to generate corresponding predicted outputs, generate corresponding client gradients based on the corresponding predicted outputs, and transmit the corresponding client gradients to the remote system. Processor(s) of the remote system can process remote data obtained from remote database(s) using global ML model(s) to generate additional corresponding predicted outputs, generate corresponding remote gradients based on the additional corresponding predicted outputs. Further, the remote system can utilize the corresponding client gradients and the corresponding remote gradients to update the global ML model(s) or weights thereof.
    Type: Grant
    Filed: July 5, 2023
    Date of Patent: January 21, 2025
    Assignee: GOOGLE LLC
    Inventors: Françoise Beaufays, Andrew Hard, Swaroop Indra Ramaswamy, Om Dipakbhai Thakkar, Rajiv Mathews
  • Publication number: 20230352004
    Abstract: Implementations disclosed herein are directed to federated learning of machine learning (“ML”) model(s) based on gradient(s) generated at corresponding client devices and a remote system. Processor(s) of the corresponding client devices can process client data generated locally at the corresponding client devices using corresponding on-device ML model(s) to generate corresponding predicted outputs, generate corresponding client gradients based on the corresponding predicted outputs, and transmit the corresponding client gradients to the remote system. Processor(s) of the remote system can process remote data obtained from remote database(s) using global ML model(s) to generate additional corresponding predicted outputs, generate corresponding remote gradients based on the additional corresponding predicted outputs. Further, the remote system can utilize the corresponding client gradients and the corresponding remote gradients to update the global ML model(s) or weights thereof.
    Type: Application
    Filed: July 5, 2023
    Publication date: November 2, 2023
    Inventors: Françoise Beaufays, Andrew Hard, Swaroop Indra Ramaswamy, Om Dipakbhai Thakkar, Rajiv Mathews
  • Patent number: 11749261
    Abstract: Implementations disclosed herein are directed to federated learning of machine learning (“ML”) model(s) based on gradient(s) generated at corresponding client devices and a remote system. Processor(s) of the corresponding client devices can process client data generated locally at the corresponding client devices using corresponding on-device ML model(s) to generate corresponding predicted outputs, generate corresponding client gradients based on the corresponding predicted outputs, and transmit the corresponding client gradients to the remote system. Processor(s) of the remote system can process remote data obtained from remote database(s) using global ML model(s) to generate additional corresponding predicted outputs, generate corresponding remote gradients based on the additional corresponding predicted outputs. Further, the remote system can utilize the corresponding client gradients and the corresponding remote gradients to update the global ML model(s) or weights thereof.
    Type: Grant
    Filed: March 10, 2021
    Date of Patent: September 5, 2023
    Assignee: GOOGLE LLC
    Inventors: Françoise Beaufays, Andrew Hard, Swaroop Indra Ramaswamy, Om Dipakbhai Thakkar, Rajiv Mathews
  • Publication number: 20220383204
    Abstract: Implementations relate to ascertaining to what extent predictions, generated using a machine learning model, can be effectively reconstructed from model updates, where the model updates are generated based on those predictions and based on applying a particular loss technique (e.g., a particular cross-entropy loss technique). Some implementations disclosed generate measures that each indicate a degree of conformity between a corresponding reconstruction, generated using a corresponding model update, and a corresponding prediction. In some of those implementations, the measures are utilized in determining whether to utilize the particular loss technique (utilized in generating the model updates) in federated learning of the machine learning model and/or of additional machine learning model(s).
    Type: Application
    Filed: November 24, 2021
    Publication date: December 1, 2022
    Inventors: Om Dipakbhai Thakkar, Trung Dang, Swaroop Indra Ramaswamy, Rajiv Mathews, Françoise Beaufays
  • Publication number: 20220293093
    Abstract: Implementations disclosed herein are directed to federated learning of machine learning (“ML”) model(s) based on gradient(s) generated at corresponding client devices and a remote system. Processor(s) of the corresponding client devices can process client data generated locally at the corresponding client devices using corresponding on-device ML model(s) to generate corresponding predicted outputs, generate corresponding client gradients based on the corresponding predicted outputs, and transmit the corresponding client gradients to the remote system. Processor(s) of the remote system can process remote data obtained from remote database(s) using global ML model(s) to generate additional corresponding predicted outputs, generate corresponding remote gradients based on the additional corresponding predicted outputs. Further, the remote system can utilize the corresponding client gradients and the corresponding remote gradients to update the global ML model(s) or weights thereof.
    Type: Application
    Filed: March 10, 2021
    Publication date: September 15, 2022
    Inventors: Françoise Beaufays, Andrew Hard, Swaroop Indra Ramaswamy, Om Dipakbhai Thakkar, Rajiv Mathews