Dimension lower bounds for linear approaches to function approximation
By: Daniel Hsu
Potential Business Impact:
Finds how much data computers need to learn.
This short note presents a linear algebraic approach to proving dimension lower bounds for linear methods that solve $L^2$ function approximation problems. The basic argument has appeared in the literature before (e.g., Barron, 1993) for establishing lower bounds on Kolmogorov $n$-widths. The argument is applied to give sample size lower bounds for kernel methods.
Similar Papers
A general technique for approximating high-dimensional empirical kernel matrices
Machine Learning (Stat)
Makes computer predictions more accurate for complex data.
On the Rate of Gaussian Approximation for Linear Regression Problems
Machine Learning (Stat)
Helps computers guess better with more data.
Low-rank approximation of analytic kernels
Numerical Analysis
Makes computer math faster for science.