Daniel J Ramage DeceasedSanta Rosa, CA

2023006, Mar 2, 2023

Oct 12, 2022

17/964563

- Mountain View CA, US
Kunal Talwar - Sunnyvale CA, US
Li Zhang - Sunnyvale CA, US
Daniel Ramage - Seattle WA, US

G06N 20/00
G06K 9/62
G06F 8/65
H04L 67/10
G06F 21/62
H04L 9/40

Systems and methods for learning differentially private machine-learned models are provided. A computing system can include one or more server computing devices comprising one or more processors and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors cause the one or more server computing devices to perform operations. The operations can include selecting a subset of client computing devices from a pool of available client computing devices; providing a machine-learned model to the selected client computing devices; receiving, from each selected client computing device, a local update for the machine-learned model; determining a differentially private aggregate of the local updates; and determining an updated machine-learned model based at least in part on the data-weighted average of the local updates.

2021004, Feb 11, 2021

Nov 27, 2019

16/698548

- Mountain View CA, US
Gang Wang - Mountain View CA, US
Daniel Ramage - Mountain View CA, US
Charlie Harrison - Mountain View CA, US
Josh Karlin - Mountain View CA, US
Moti Yung - Mountain View CA, US

Google LLC - Mountain View CA

G06Q 30/02
H04L 9/32
H04L 9/08
G06F 16/951

The present disclosure provides systems and methods for content quasi-personalization or anonymized content retrieval via aggregated browsing history of a large plurality of devices, such as millions or billions of devices. A sparse matrix may be constructed from the aggregated browsing history, and dimensionally reduced, reducing entropy and providing anonymity for individual devices. Relevant content may be selected via quasi-personalized clusters representing similar browsing histories, without exposing individual device details to content providers.

2019022, Jul 25, 2019

Jan 22, 2018

15/877196

- Mountain View CA, US
Kunal Talwar - Sunnyvale CA, US
Li Zhang - Sunnyvale CA, US
Daniel Ramage - Seattle WA, US

G06F 15/18
G06F 8/65
G06K 9/62

Systems and methods for learning differentially private machine-learned models are provided. A computing system can include one or more server computing devices comprising one or more processors and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors cause the one or more server computing devices to perform operations. The operations can include selecting a subset of client computing devices from a pool of available client computing devices; providing a machine-learned model to the selected client computing devices; receiving, from each selected client computing device, a local update for the machine-learned model; determining a differentially private aggregate of the local updates; and determining an updated machine-learned model based at least in part on the data-weighted average of the local updates.

2014028, Sep 18, 2014

Mar 12, 2014

14/206880

- Mountain View CA, US
Daniel Ramage - Mountain View CA, US

GOOGLE INC. - Mountain View CA

G06F 17/30

707748

A system stores a table mapping users to attributes, and stores a second table mapping the users to products associated with a source domain. The system determines a set of top scoring products for each of the attributes, and creates, using the top scoring products, a model that is predictive of an activity in a target domain, the target domain being separate from the source domain. The system detects a behavior from a particular user accessing the target domain, and generates a personalized prediction for the particular user based on the model, in response to the detecting the behavior.