Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
cs.LG, cs.CR, stat.ML
Submitted: 2026-01-29
Updated: 2026-11-06
Code: https://github.com/google-deepmind/jax_privacy
Terminology
Sources
- Efficient and Scalable Implementation of Differentially Private Deep Learning without Shortcuts
- Efficient privacy loss accounting for subsampling and random allocation
- Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
- Correlated Noise Mechanisms for Differentially Private Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis