On the space of inner products used in kernel ridge regression, a covariance-weighted gradient flow is proved to converge, preserve rank, and monotonically suppress independent Gaussian noise.
Bach,Learning Theory from First Principles, MIT Press, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gradient flow in the kernel learning problem
On the space of inner products used in kernel ridge regression, a covariance-weighted gradient flow is proved to converge, preserve rank, and monotonically suppress independent Gaussian noise.