Patents by Inventor Steffen Rendle

Steffen Rendle 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).

  • PRIVACY-ENHANCED TRAINING AND DEPLOYMENT OF MACHINE LEARNING MODELS USING CLIENT-SIDE AND SERVER-SIDE DATA
    Publication number: 20240054391
    Abstract: Computer-implemented systems and methods for training a decentralized model for making a personalized recommendation.
    Type: Application
    Filed: April 5, 2022
    Publication date: February 15, 2024
    Inventors: Abhradeep Guha Thakurta, Li Zhang, Prateek Jain, Shuang Song, Steffen Rendle, Steve Shaw-Tang Chien, Walid Krichene, Yarong Mu
  • Robust large-scale machine learning in the cloud
    Patent number: 10482392
    Abstract: The present disclosure provides a new scalable coordinate descent (SCD) algorithm and associated system for generalized linear models whose convergence behavior is always the same, regardless of how much SCD is scaled out and regardless of the computing environment. This makes SCD highly robust and enables it to scale to massive datasets on low-cost commodity servers. According to one aspect, by using a natural partitioning of parameters into blocks, updates can be performed in parallel a block at a time without compromising convergence. Experimental results on a real advertising dataset are used to demonstrate SCD's cost effectiveness and scalability.
    Type: Grant
    Filed: February 10, 2017
    Date of Patent: November 19, 2019
    Assignee: Google LLC
    Inventors: Steffen Rendle, Dennis Craig Fetterly, Eugene J. Shekita, Bor-yiing Su
  • Robust Large-Scale Machine Learning in the Cloud
    Publication number: 20170236072
    Abstract: The present disclosure provides a new scalable coordinate descent (SCD) algorithm and associated system for generalized linear models whose convergence behavior is always the same, regardless of how much SCD is scaled out and regardless of the computing environment. This makes SCD highly robust and enables it to scale to massive datasets on low-cost commodity servers. According to one aspect, by using a natural partitioning of parameters into blocks, updates can be performed in parallel a block at a time without compromising convergence. Experimental results on a real advertising dataset are used to demonstrate SCD's cost effectiveness and scalability.
    Type: Application
    Filed: February 10, 2017
    Publication date: August 17, 2017
    Inventors: Steffen Rendle, Dennis Craig Fetterly, Eugene J. Shekita, Bor-yiing Su