collaborators

6 papers

stat.ML2026

Lipschitz Continuity in Deep Learning: A Systematic Review of Theoretical Foundations, Estimation Methods, Regularization Approaches, and Certifiable Robustness

Róisín Luo, James McDermott, Colm O'Riordan

Lipschitz continuity is a fundamental property of neural networks that characterizes their sensitivity to input perturbations. It plays a pivotal role in deep learning, governing \…

cs.AI2026

Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition

Róisín Luo, James McDermott, Colm O'Riordan

Perturbation robustness evaluates the vulnerabilities of models, arising from a variety of perturbations, such as data corruptions and adversarial attacks. Understanding the mechan…

cs.CV2026

Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization

Róisín Luo, Alexandru Drimbarean, James McDermott +1

This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, differing from existing state-of-the-art methods, by framing optimal quantization as an archite…

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 opera…

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…