Learning discrete distributions with infinite support
–Neural Information Processing Systems
In such a setting, distribution-free risk bounds are impossible, and the best one could hope for is a fully empirical data-dependent bound.
Neural Information Processing Systems
Nov-13-2025, 14:42:11 GMT
- Country:
- Asia
- Japan > Kyūshū & Okinawa
- Okinawa (0.04)
- Middle East > Israel
- Southern District > Beer-Sheva (0.04)
- Japan > Kyūshū & Okinawa
- Europe
- France > Île-de-France
- United Kingdom > England
- Cambridgeshire > Cambridge (0.14)
- North America
- Canada > Quebec
- Montreal (0.04)
- United States
- Arizona > Maricopa County
- Phoenix (0.04)
- Nebraska > Lancaster County
- Lincoln (0.14)
- Arizona > Maricopa County
- Canada > Quebec
- Asia
- Technology: