Contraction and Statistical Inference under Privacy for Uniformly Bounded Distributions

arXiv:2609.28297 · cs.IT, cs.CR, math.IT, math.ST, stat.TH · Submitted 2026-09-23 · Read on arXiv

cs.IT, cs.CR, math.IT, math.ST, stat.TH

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/ccanonne/probabilitydistributiontoolbox

Terminology

• Differential Privacy — 35× in this paper · explained in 4 episodes
• Sample Complexity — 16× in this paper · explained in 15 episodes
• EMMA — 7× in this paper · explained in 2 episodes
• Differentially Private — 4× in this paper · explained in 3 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• IEEE International Symposium on Information Theory — 4× in this paper
• Core — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Adversarial Attacks — 2× in this paper · explained in 1 episode
• Fisher Information — 2× in this paper · explained in 3 episodes
• Information Leakage — 2× in this paper · explained in 2 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Adaptive Weighting — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Differential Privacy (DP) — 1× in this paper · explained in 7 episodes
• Federated Learning — 1× in this paper · explained in 15 episodes
• Hamming Distance — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes

Sources

• Scalable Private Partition Selection via Adaptive Weighting
• Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
• Local and Global Contraction Principles for MCMC Mixing
• Contraction of $E_\gamma$-Divergence and Its Applications to Privacy
• Non-Linear Strong Data-Processing for Quantum Hockey-Stick Divergences
• On the strong converses for the quantum channel capacity theorems
• Variational formulas for the power of the binary hypothesis testing problem with applications
• Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
• Contraction of R'enyi Divergences for Discrete Channels: Properties and Applications
• A Short Proof of Strassen's Theorem Using Convex Analysis

Related papers

• Clipped Affine Policy: Low-Complexity Near-Optimal Online Power Control for Energy Harvesting Communications over Fading Channels
• Discrepancy for Random Linear Codes
• A New Approach to Code Smoothing Bounds
• Contextual Memory-Enhanced Source Coding for Low-SNR Communications
• Symmetry-Enforced Quadratic Approximate-Degradability Bounds for Noisy Landau-Streater Channels
• Anonymous Shamir's Secret Sharing via Reed-Solomon Codes Against Permutations, Insertions, and Deletions