{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11475350","patent":{"patent_number":"US-11475350","title":"Training user-level differentially private machine-learned models","assignee":null,"inventors":[],"filing_date":"2018-01-22T00:00:00.000Z","publication_date":"2022-10-18T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06F","G06N","G06N","G06N","G06N","G06N","H04L","H04L","G06N","G06V","G06V"],"num_claims":20,"abstract":"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."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Training user-level differentially private machine-learned models","description":"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 o","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11475350","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11475350","citation_suggestion":"Patentable. \"Training user-level differentially private machine-learned models\" (US-11475350). https://patentable.app/patents/US-11475350","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11475350","json":"https://patentable.app/api/llm-context/US-11475350","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T09:24:41.485Z"}