What is recorded here?
Applied user-adjacent DP to language-model training using independently sampled users, clipped user updates, bounded-sensitivity averaging estimators, Gaussian noise and moments accounting.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Guarantee concerns adding/removing an entire user's data under specified sampling/estimator/clipping/accounting assumptions, not cryptographic concealment from a trusted curator. Accuracy preservation was demonstrated at substantial computation cost on a sufficiently large dataset, not free privacy or all datasets.2017 v1 title Language Models differs from later Recurrent Language Models.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
H. Brendan McMahan; Daniel Ramage; Kunal Talwar; Li Zhang
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
User-level private language-model training with clipped federated updates
Applied user-adjacent DP to language-model training using independently sampled users, clipped user updates, bounded-sensitivity averaging estimators, Gaussian noise and moments accounting.
Scientific scope
Guarantee concerns adding/removing an entire user's data under specified sampling/estimator/clipping/accounting assumptions, not cryptographic concealment from a trusted curator. Accuracy preservation was demonstrated at substantial computation cost on a sufficiently large dataset, not free privacy or all datasets.2017 v1 title Language Models differs from later Recurrent Language Models.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
H. Brendan McMahan; Daniel Ramage; Kunal Talwar; Li Zhang
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.