Mathias Dus

Radon Measure Representations for Infinite-Width Neural Networks with Singular Activations

2026 · HAL (Le Centre pour la Communication Scientifique Directe)

The theoretical foundation of infinite-width shallow neural networks relies heavily on continuous integral representations and Barron spaces. Recently, harmonic analysis-specifically the Radon and Ridgelet transforms-has emerged as a powerful tool to invert these representations and …