Aug 16, 2022 · In this paper, we consider Barron functions f : [0,1]^d \to \mathbb{R} of smoothness \sigma > 0, which are functions that can be written as f(x ...

For these functions, we study the following question: Given $m$ point samples $f(x_1),\dots,f(x_m)$ of an unknown Barron function $f : [0,1]^d \to \mathbb{R}$ ...

Aug 16, 2022 · Barron functions and sampling numbers that we will use. 1.1 Definition of the Barron space and sampling numbers. In this paper, we will study ...

In this paper, we consider Barron functions $f : [0,1]^d \to \mathbb{R}$ of smoothness $\sigma>0$, which are functions that can be written as \[ f(x) ...

We describe the conditions under which the least squares procedures and Fourier analytic methods do not produce estimates close to maximum likelihood, and show ...

In this paper, we consider Barron functions f : [0,1]^d →ℝ of smoothness σ > 0, which are functions that can be written as f(x) = ∫_ℝ^d F(ξ) e^2 π i ⟨ x, ...

Aug 22, 2022 · Bibliographic details on $L^p$ sampling numbers for the Fourier-analytic Barron space.

Dec 2, 2022 · ... L^p, then the optimal reconstruction error behaves like O(N^{−1/d−1/max{p,2}}), up to log factors. The proof combines results and ...

In this paper, we consider Barron functions $f : [0,1]^d \to \mathbb{R}$ of smoothness $\sigma > 0$, which are functions that can be written as \[ f(x) ...

L p sampling numbers for the Fourier-analytic Barron space · no code implementations • 16 Aug 2022 • Felix Voigtlaender. In this paper, we consider Barron ...