Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacy
–Neural Information Processing Systems
Differentially private (DP) machine learning algorithms incur many sources of randomness, such as random initialization, random batch subsampling, and shuffling.
Neural Information Processing Systems
Oct-9-2025, 04:33:16 GMT
- Country:
- North America > United States
- Pennsylvania > Philadelphia County
- Philadelphia (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- Maryland > Montgomery County
- Bethesda (0.04)
- Georgia > Fulton County
- Atlanta (0.04)
- Colorado > Denver County
- Denver (0.04)
- California
- Santa Barbara County > Santa Barbara (0.04)
- San Diego County > San Diego (0.04)
- Los Angeles County
- Los Angeles (0.14)
- Long Beach (0.04)
- Pennsylvania > Philadelphia County
- Europe
- Austria > Vienna (0.14)
- Latvia > Riga Municipality
- Riga (0.04)
- Italy > Tuscany
- Florence (0.04)
- Germany > Hesse
- Darmstadt Region > Darmstadt (0.04)
- France
- Île-de-France > Paris
- Paris (0.04)
- Nouvelle-Aquitaine > Gironde
- Bordeaux (0.04)
- Île-de-France > Paris
- Asia
- Middle East > Jordan (0.04)
- Singapore > Central Region
- Singapore (0.04)
- Japan > Kyūshū & Okinawa
- Okinawa (0.04)
- China
- Guangdong Province > Shenzhen (0.04)
- Shaanxi Province > Xi'an (0.04)
- North America > United States
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology: