An Improved Empirical Fisher Approximation for Natural Gradient Descent
–Neural Information Processing Systems
Despite its ease of implementation, the EF approximation has its theoretical and practical limitations.
Neural Information Processing Systems
Nov-20-2025, 06:48:16 GMT
- Country:
- Asia (0.14)
- Europe
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- France > Hauts-de-France
- Germany > Bavaria
- Lower Franconia > Würzburg (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Belgium > Brussels-Capital Region
- North America
- Canada > British Columbia
- Vancouver (0.04)
- Dominican Republic (0.04)
- United States
- California > San Diego County
- San Diego (0.04)
- Georgia > Fulton County
- Atlanta (0.04)
- Indiana > Hamilton County
- Fishers (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- California > San Diego County
- Canada > British Columbia
- Oceania > Australia
- New South Wales > Sydney (0.04)
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Education (0.67)
- Technology: