Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
–Neural Information Processing Systems
In this work, we conduct a systematic study of stochastic saddle point problems (SSP) and stochastic variational inequalities (SVI) under the constraint of (ϵ, δ)- differential privacy (DP) in both Euclidean and non-Euclidean setups.
Neural Information Processing Systems
Mar-27-2025, 13:13:03 GMT
- Country:
- North America
- Canada > Ontario
- Toronto (0.14)
- United States (0.46)
- Canada > Ontario
- North America
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Information Technology > Security & Privacy (0.67)
- Technology: