
Quantitative Rates and Fundamental Obstructions to NonEuclidean Universal Approximation with Deep Narrow FeedForward Networks
By incorporating structured pairs of nontrainable input and output laye...
read it

Optimizing Optimizers: Regretoptimal gradient descent algorithms
The need for fast and robust optimization algorithms are of critical imp...
read it

Overcoming The Limitations of Neural Networks in CompositePattern Learning with Architopes
The effectiveness of neural networks in solving complex problems is well...
read it

Architopes: An Architecture Modification for Composite Pattern Learning, Increased Expressiveness, and Reduced Training Time
We introduce a simple neural network architecture modification that enab...
read it

NonEuclidean Universal Approximation
Modifications to a neural network's input and output layers are often re...
read it

Universal Approximation Theorems
The universal approximation theorem established the density of specific ...
read it

The NEU MetaAlgorithm for Geometric Learning with Applications in Finance
We introduce a metaalgorithm, called nonEuclidean upgrading (NEU), whi...
read it

Geometric Learning and Filtering in Finance
We develop a method for incorporating relevant nonEuclidean geometric i...
read it

ArbitrageFree Regularization
We introduce a pathdependent geometric framework which generalizes the ...
read it