no code implementations • 7 Nov 2023 • Kohei Miyamoto, Andrew R. Barron, Jun'ichi Takeuchi
Minimum Description Length (MDL) estimators, using two-part codes for universal coding, are analyzed.
no code implementations • 2 Feb 2019 • Andrew R. Barron, Jason M. Klusowski
For any ReLU network there is a representation in which the sum of the absolute values of the weights into each node is exactly $1$, and the input layer variables are multiplied by a value $V$ coinciding with the total variation of the path weights.
no code implementations • 10 Sep 2018 • Andrew R. Barron, Jason M. Klusowski
It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations.
no code implementations • 9 Feb 2017 • Jason M. Klusowski, Andrew R. Barron
Estimation of functions of $ d $ variables is considered using ridge combinations of the form $ \textstyle\sum_{k=1}^m c_{1, k} \phi(\textstyle\sum_{j=1}^d c_{0, j, k}x_j-b_k) $ where the activation function $ \phi $ is a function with bounded value and derivative.
no code implementations • 26 Jul 2016 • 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 ridge functions with $ \ell^1 $ and $ \ell^0 $ controls on their inner and outer parameters.
no code implementations • 5 Jul 2016 • Jason M. Klusowski, Andrew R. Barron
On the other hand, if the candidate fits are chosen from a discretization, we show that $ \mathbb{E}\|\hat{f} - f^{\star} \|^2 \leq \left(v^3_{f^{\star}}\frac{\log d}{n}\right)^{2/5} $.