The Fast Mixing Mechanism for Differential Privacy

arXiv:2605.30600 · cs.LG, cs.IT, math.IT · Submitted 2026-08-20 · Read on arXiv

Omri Lev, Moshe Shenfeld, Vishwak Srinivasan, Katrina Ligett, Ashia C. Wilson

cs.LG, cs.IT, math.IT

Submitted: 2026-08-20

Updated: 2026-08-24

Code: https://github.com/omrilev1/FastMix

Terminology

• Accuracy — 25× in this paper · explained in 1 episode
• Differential Privacy — 23× in this paper · explained in 4 episodes
• Subsampled Randomized Hadamard Transform — 6× in this paper
• Differentially Private — 4× in this paper · explained in 3 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Differential Privacy (DP) — 3× in this paper · explained in 7 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Positive Semi-Definite — 1× in this paper
• Sample Complexity — 1× in this paper · explained in 15 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Randomness Efficient Fast-Johnson-Lindenstrauss Transform with Applications in Differential Privacy and Compressed Sensing

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks