A. Barron

activity

20012022

most citedApproximation and learning by greedy algorithms

323 citations · 747 across the 16 of their papers we have counts for

collaborators

Showing 2016Show all

2 papers · 1 filter

stat.ML2016★ 8 cited

Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with $ℓ^{1}$ and $ℓ^{0}$ Controls

Jason M. Klusowski, Andrew R. Barron

We establish $L^{\infty}$ and $L^{2}$ error bounds for functions of many variables that are approximated by linear combinations of ReLU (rectified linear unit) and squared ReLU r…

math.ST2016★ 30 cited

Risk Bounds for High-dimensional Ridge Function Combinations Including Neural Networks

Jason M. Klusowski, Andrew R. Barron

Let $f^{⋆}$ be a function on $R^{d}$ with an assumption of a spectral norm $v_{f^{⋆}}$ . For various noise settings, we show that $ \mathbb{E}\|\hat{f} - f^{\st…

Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with ℓ1 and ℓ0 Controls

Risk Bounds for High-dimensional Ridge Function Combinations Including Neural Networks

Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with $ℓ^{1}$ and $ℓ^{0}$ Controls