Differentially Private Synthetic Data from Sliced Chebyshev Moments
cs.LG, cs.CY, cs.DS
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/lurosenb/splice
Terminology
Sources
- Sharp bounds for max-sliced Wasserstein distances
- Sharp comparisons between sliced and standard $1$-Wasserstein distances
- Minimax optimal differentially private synthetic data for smooth queries
- PREM: Privately Answering Statistical Queries with Relative Error
- Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics
- Nearly sharp comparison results for sliced and max-sliced Wasserstein distances
- Differentially Private Synthetic Data: Applied Evaluations and Enhancements
- Are Data Experts Buying into Differentially Private Synthetic Data? Gathering Community Perspectives
- Moments and Absolute Moments of the Normal Distribution
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis