The dense-feature NTK amplitude-optimization strategy is described as viable only for small 1D regression problems; dense multidimensional frequency sampling is not tractable because of memory constraints and growth of the basis with dimension. · CiteArk
Not assessedNo independent reproduction scheduledLimitationlimitation-dense-high-dimensional
The dense-feature NTK amplitude-optimization strategy is described as viable only for small 1D regression problems; dense multidimensional frequency sampling is not tractable because of memory constraints and growth of the basis with dimension.
Source: paper:§5 p. 6; §A.1 p. 12
Reported and observed measurements
No structured measurement is attached to this Claim.
Assessments (0)
No immutable Assessment has been published for this Claim yet.
