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) **Files:**- Universal_JSD_Shuffle_Model.pdf — unified theory- jsd_shuffle.pdf — binary case (BSC)- jsd_k_rr_shuffle_v2.pdf — k-ary generalization- addon2.pdf — complete proof of O(n⁻²) remainder- main.pdf — arXiv submission version (LaTeX with figures) **Code:** https://github.com/alt178332/jsd-contraction Author: Alex ShvetsORCID: 0009-0005-9802-379X
Fields of Study & Subjects
Markov Chains and Monte Carlo Methods
Random Matrices and Applications
Theoretical and Computational Physics
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 8 January 2026
- Language
- EN
- Document type
- Preprint