Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling
From Google TechTalks · 1:04:38
Show by Google TechTalks
A Google TechTalk, 2026-02-18, presented by Andy DongABSTRACT: DP-SGD remains the standard approach for private model training. A variety of techniques have been developed to improve its privacy–utility tradeoff, including privacy amplification through data subsampling, leveraging structured randomness in the training process, and correlated-noise mechanisms such as DP matrix factorization (DP-MF). While DP-MF can improve utility, its interaction with subsampling-based amplification is less explored than in the classical DP-SGD setting.Uploaded 09-06-26In this talk, I present b-min-sep subsampling, a simple batching scheme for DP-MF. The key idea is to impose only a minimal participation constraint that preserves the structural properties required by correlated-noise mechanisms, while retaining substantial flexibility in sampling. The resulting scheme improves over cyclic Poisson subsampling and is a generalization of balls-in-bins subsampling.I will give a high-level overview of the privacy analysis based on Monte Carlo accounting and dynamic programming, and present empirical results demonstrating improved privacy–utility tradeoffs in both example-level and multi-attribution user-level settings. More broadly, this work fits into a line of research on leveraging randomness in training for privacy amplification.
More episodes of Google TechTalks
More episodes
- The Limits and Possibilities of One Run Auditing
- PhotoTechEDU Day 29: Photographing VR Panoramas
- Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
- Inside VMware Fusion
- Java Posse Episode 100 (Live Special)
- Cascading Adversarial Bias from Injection to Distillation in Language Models
- Practical Common Lisp
- Cascading Adversarial Bias from Injection to Distillation in Language Models
- Security is Broken
- POPri: Private Federated Learning using Preference-Optimized Synthetic Data
PodSearch is a free, independent podcast search engine. Read about PodSearch, the privacy policy or contact us.