no code implementations • 11 Oct 2023 • Guergana Petrova, Przemyslaw Wojtaszczyk
We give estimates from below for the error of approximation of a compact subset from a Banach space by the outputs of feed-forward neural networks with width W, depth l and Lipschitz activation functions.
no code implementations • 30 Nov 2022 • Guergana Petrova, Przemysław Wojtaszczyk
Our results are obtained as a byproduct of the study of the recently introduced Lipschitz widths.
no code implementations • 30 Mar 2022 • Peter Binev, Andrea Bonito, Ronald DeVore, Guergana Petrova
The learning problem is to give an approximation $\hat f$ to $f$ that predicts the values of $f$ away from the data.
no code implementations • 28 Jul 2021 • Ingrid Daubechies, Ronald DeVore, Nadav Dym, Shira Faigenbaum-Golovin, Shahar Z. Kovalsky, Kung-Ching Lin, Josiah Park, Guergana Petrova, Barak Sober
Namely, we show that refinable functions are approximated by the outputs of deep ReLU networks with a fixed width and increasing depth with accuracy exponential in terms of their number of parameters.