2 papers
math.OC2025
OCTANE -- Optimal Control for Tensor-based Autoencoder Network Emergence: Explicit Case
Ratna Khatri, Anthony Kolshorn, Colin Olson +1
This paper presents a novel, mathematically rigorous framework for autoencoder-type deep neural networks that combines optimal control theory and low-rank tensor methods to yield m…
stat.ML2025
ROCK: A variational formulation for occupation kernel methods in Reproducing Kernel Hilbert Spaces
Victor Rielly, Kamel Lahouel, Chau Nguyen +3
We present a Representer Theorem result for a large class of weak formulation problems. We provide examples of applications of our formulation both in traditional machine learning…