ATheoryofPACLearnabilityunderTransformation Invariances
–Neural Information Processing Systems
Third, weintroduce acomplexitymeasure (seeDefinition 5)thatcharacterizes theoptimal sample complexity of learning in settings (ii) and (iii) above, and we give optimal algorithms for these settings. Finally,wealso provide adaptivelearning algorithms that interpolate between settings (i) and (ii), i.e., whenh is partiallyinvariant.
Neural Information Processing Systems
Feb-9-2026, 05:30:34 GMT
- Country:
- Asia > Japan
- Honshū > Tōhoku > Fukushima Prefecture > Fukushima (0.04)
- Europe > Russia
- Central Federal District > Moscow Oblast > Moscow (0.04)
- North America > United States
- Illinois > Cook County > Chicago (0.04)
- Asia > Japan
- Technology: