Intrinsic-Dimensional Wasserstein Guarantees for Private Synthetic Measures

arXiv:2609.17624 · cs.DS, cs.CR, cs.IT, math.IT, math.PR · Submitted 2026-09-15 · Read on arXiv

cs.DS, cs.CR, cs.IT, math.IT, math.PR

Submitted: 2026-09-15

Updated: 2026-09-15

Comments: 30 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Differentially Private — 26× in this paper · explained in 3 episodes
• Differential Privacy — 17× in this paper · explained in 4 episodes
• Intrinsic Dimension — 15× in this paper · explained in 2 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Ambient Dimension — 8× in this paper · explained in 1 episode
• Wasserstein Distance — 7× in this paper · explained in 4 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Adaptive Partitioning — 2× in this paper · explained in 1 episode
• Clustering — 2× in this paper · explained in 2 episodes
• Curse of Dimensionality — 2× in this paper · explained in 6 episodes
• Optimal Transport — 2× in this paper · explained in 5 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Synthetic Data Generation — 1× in this paper · explained in 5 episodes

Related papers

• Cascaded Learned Bloom Filter for Optimizing Model-Filter Size Balance and Fast Rejection
• Edge-Private Matching Kernels Through Local Decoding
• Local Node Differential Privacy
• Cheaper by the Batch: Shared Traversal for Genotype Graph Editing
• Scalable Algorithms for Approximate DNF Model Counting
• On the Approximation Relationship between Optimizing Ratio of Submodular (RS) and Difference of Submodular (DS) Functions