JSD Bounds for the Shuffle Model: Universal Formula via Chi-Squared Divergence
Abstract
For any binary-input local randomizer with output distributions W₀, W₁: JSD(Tₙ ‖ Tₙ') = χ²(W₁‖W₀)/(8n) + O(n⁻²) **Special cases:** - Binary RR: χ² = (1−2δ)²/[δ(1−δ)] - k-ary RR: χ² = η_k(ε) with explicit formula
Fields of Study & Subjects
Random Matrices and Applications
Markov Chains and Monte Carlo Methods
Stochastic processes and statistical mechanics
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 1 January 2026
- Language
- EN
- Document type
- Preprint