Abstract: Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.

Abstract: A method include obtaining a set of differentially private (DP) gradients each generated based on processing corresponding private data, and obtaining a set of public gradients each generated based on processing corresponding public data. The method also includes applying mirror descent to the set of public gradients to learn a geometry for the set of DP gradients, and reshaping the set of DP gradients based on the learned geometry. The method further includes training a machine learning model based on the reshaped set of DP gradients.

Abstract: Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.

Abstract: Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.

Abstract: A computer system may include a processor and a memory coupled thereto. The memory may include a database. The processor may be configured to randomly split the database into sub-databases and applying a database query to the sub-databases. The processor may also be configured to generate respective estimated query response values for each sub-database based upon applying the database query, calculate a median of the estimated query response values, and generate a probability distribution based upon the estimated query response values and the calculated median. The processor may further be configured to select a final estimated query response value based upon the probability distribution.

Abstract: Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.

Abstract: A computer system may include a processor and a memory coupled thereto. The memory may include a database. The processor may be configured to randomly split the database into sub-databases and applying a database query to the sub-databases. The processor may also be configured to generate respective estimated query response values for each sub-database based upon applying the database query, calculate a median of the estimated query response values, and generate a probability distribution based upon the estimated query response values and the calculated median. The processor may further be configured to select a final estimated query response value based upon the probability distribution.

Abstract: In preferred embodiments, this invention relates to an expandable stent, comprising a tubular member comprising at least two circumferentially-adjacent radial elements, wherein each radial element comprises an engagement slot, through which a portion of the circumferentially-adjacent radial element is slidably engaged, such that the tubular member is capable of expanding from a first collapsed diameter to a second expanded diameter, wherein the engagement slot is not a paired slot.

Abstract: The present invention provides a lumen support stent with a clear through-lumen for use in a body lumen. The stent is formed from at least one series of sliding and locking radial elements and at least one ratcheting mechanism comprising an articulating element and a plurality of stops. The ratcheting mechanism permits one-way sliding of the radial elements from a collapsed diameter to an expanded diameter, but inhibits radial recoil from the expanded diameter.

Abstract: An apparatus and method of manufacturing a wire mesh laminate includes wrapping a central core with multiple layers of mesh screen and a barrier layer having a higher melting point than the mesh screen to form a spool assembly. The spool assembly is then surrounded by an outer cover and is heated to sinter or fuse together the layers of mesh screen.

Abstract: An apparatus and method of manufacturing a wire mesh laminate includes wrapping a central core with multiple layers of mesh screen and a barrier layer having a higher melting point than the mesh screen to form a spool assembly. The spool assembly is then surrounded by an outer cover and is heated to sinter or fuse together the layers of mesh screen.