Stability and error guarantees for least squares approximation with noisy samples

04/09/2022
by   Felix Bartel, et al.
0

Given n samples of a function f : D→ℂ in random points drawn with respect to a measure ν we develop theoretical analysis of the L_2(D, μ)-approximation error. We show that the weighted least squares method from finite dimensional function spaces V_m, (V_m) = m < ∞ is stable and optimal up to a multiplicative constant when given exact samples with logarithmic oversampling. Further, for noisy samples, our bounds describe the bias-variance trade off depending on the dimension m of the approximation space V_m. All results hold with high probability. For demonstration, we consider functions defined on the d-dimensional cube given in unifom random samples. We analyze polynomials, the half-perid cosine, and a bounded orthonormal basis of the non-periodic Sobolev space H_mix^2. Overcoming numerical issues of this H_mix^2 basis, this gives a novel stable approximation method with quadratic error decay. Numerical experiments indicate the applicability of our results.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset