An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions
–Neural Information Processing Systems
We propose ResidualPlanner, a matrix mechanism for marginals with Gaussian noise that is both optimal and scalable.
Neural Information Processing Systems
Feb-10-2026, 23:16:55 GMT
- Country:
- Europe > Ireland
- Leinster > County Dublin > Dublin (0.04)
- North America > United States (0.14)
- Europe > Ireland
- Genre:
- Research Report (0.67)
- Industry:
- Information Technology > Security & Privacy (0.67)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning (1.00)
- Natural Language (0.67)
- Representation & Reasoning > Optimization (0.46)
- Data Science > Data Mining (0.68)
- Security & Privacy (0.67)
- Artificial Intelligence
- Information Technology