Metric Transforms and Low Rank Representations of Kernels for Fast Attention
–Neural Information Processing Systems
This suggests that the low-rank fast attention only works for functions approx-imable by polynomials.
Neural Information Processing Systems
Oct-10-2025, 02:47:47 GMT
- Country:
- Asia
- China > Hong Kong (0.04)
- Middle East > Jordan (0.04)
- Russia (0.04)
- Europe
- Germany > North Rhine-Westphalia
- Upper Bavaria > Munich (0.04)
- Russia (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Germany > North Rhine-Westphalia
- North America > United States
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- Wisconsin > Dane County
- Madison (0.04)
- Pennsylvania > Allegheny County
- South America > Brazil
- Rio de Janeiro > Rio de Janeiro (0.04)
- Asia
- Genre:
- Research Report
- Experimental Study (0.92)
- New Finding (1.00)
- Research Report
- Industry:
- Education (0.45)
- Information Technology (0.45)
- Technology: