3 papers
cs.CV2025
Sampling Matters in Explanations: Towards Trustworthy Attribution Analysis Building Block in Visual Models through Maximizing Explanation Certainty
Róisín Luo, James McDermott, Colm O'Riordan
Image attribution analysis seeks to highlight the feature representations learned by visual models such that the highlighted feature maps can reflect the pixel-wise importance of i…
cs.LG2025
Optimization-Induced Dynamics of Lipschitz Continuity in Neural Networks
Róisín Luo, James McDermott, Christian Gagné +2
Lipschitz continuity characterizes the worst-case sensitivity of neural networks to small input perturbations; yet its dynamics (i.e. temporal evolution) during training remains un…
stat.ML2025
Higher-Order Singular-Value Derivatives of Rectangular Real Matrices
Róisín Luo, James McDermott, Colm O'Riordan
We present a theoretical framework for deriving the general -th order Fréchet derivatives of singular values in real rectangular matrices, by leveraging reduced resolvent operat…