Fast Privacy Loss Accounting for Random Allocation via Multiscale FFT
cs.LG
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/google/differential-
Terminology
Sources
- Privacy Amplification for BandMF via $b$-Min-Sep Subsampling
- Concentrated Differential Privacy
- Efficient privacy loss accounting for subsampling and random allocation
- Gaussian Approximation for Composition and Subsampling of Differentially Private Algorithms
- Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT
- Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
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