collaborators

6 papers

cs.LG2026

A Learning Stability Profile for Finite-Dimensional Learning Dynamics

Ronald Katende

We develop a finite-dimensional sensitivity framework for studying stability in learning systems whose states include representations, parameters, and update variables. The central…

cs.LG2026

A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems

Ronald Katende

Modern learning systems often interpolate training data while still generalizing well, yet it remains unclear when algorithmic stability explains this behavior. We model training a…

cs.LG2026

A Unified Matrix-Spectral Framework for Stability and Interpretability in Deep Learning

Ronald Katende

We develop a unified matrix-spectral framework for analyzing stability and interpretability in deep neural networks. Representing networks as data-dependent products of linear oper…

cs.LG2025

Why Smooth Stability Assumptions Fail for ReLU Learning

Ronald Katende

Stability analyses of modern learning systems are frequently derived under smoothness assumptions that are violated by ReLU-type nonlinearities. In this note, we isolate a minimal…

cs.LG2025

Non-Asymptotic Stability and Consistency Guarantees for Physics-Informed Neural Networks via Coercive Operator Analysis

Ronald Katende

We present a unified theoretical framework for analyzing the stability and consistency of Physics-Informed Neural Networks (PINNs), grounded in operator coercivity, variational for…

cs.LG2025

Unified theoretical guarantees for stability, consistency, and convergence in neural PDE solvers from non-IID data to physics-informed networks

Ronald Katende

We establish a unified theoretical framework addressing the stability, consistency, and convergence of neural networks under realistic training conditions, specifically, in the pre…