3 papers
stat.ML2026
Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity
Julia Nakhleh, Robert D. Nowak
We develop a unified function space theory of deep fully connected neural networks. Functions in our spaces are defined recursively as -bounded linear combinations of activ…
stat.ML2026
Global Minimizers of -Regularized Objectives Yield the Sparsest ReLU Neural Networks
Julia Nakhleh, Robert D. Nowak
Overparameterized neural networks can interpolate a given dataset in many different ways, prompting the fundamental question: which among these solutions should we prefer, and what…
stat.ML2025
The Effects of Multi-Task Learning on ReLU Neural Network Functions
Julia Nakhleh, Joseph Shenouda, Robert D. Nowak
This paper studies the properties of solutions to multi-task shallow ReLU neural network learning problems, wherein the network is trained to fit a dataset with minimal sum of squa…