Loading patent…
AssigneeGoogle Inc.
InventorsBadih Ghazi, Yangsibo Huang, Chiyuan Zhang, Pasin Manurangsi, Pritish Kamath, Shanmugasundaram Ravikumar
Estimating the term…
Aspects of the disclosure are directed to implementing a projection-based stochastic gradient descent technique that maintains label differential privacy when training one or more machine learning models. The technique includes denoising gradients by exploiting projections when training the machine learning models to improve performance of the trained machine learning models while maintaining label differential privacy. For instance, the projection-based stochastic gradient descent technique can improve performance of machine learning models in higher-privacy regimes, such as digital content management.
A method for training a machine learning model with differentially private labels comprising:
A system comprising:
A non-transitory computer readable medium for storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations for training a machine learning model with differentially private labels, the operations comprising:
Dependencies are inferred from the claim text.