102 citations · 116 across the 18 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
stat.ML2022★ 1 cited
Limitations on approximation by deep and shallow neural networks
Guergana Petrova, Przemysław Wojtaszczyk
We prove Carl's type inequalities for the error of approximation of compact sets K by deep and shallow neural networks. This in turn gives lower bounds on how well we can approxima…
cs.LG2022★ 1 cited
Optimal Learning
Peter Binev, Andrea Bonito, Ronald DeVore +1
This paper studies the problem of learning an unknown function from given data about . The learning problem is to give an approximation to that predicts the val…
math.FA2022
On the entropy numbers and the Kolmogorov widths
Guergana Petrova, Przemyslaw Wojtaszczyk
Direct estimates between linear or nonlinear Kolmogorov widths and entropy numbers are presented. These estimates are derived using the recently introduced Lipschitz widths. Applic…