Tharrshann Jayan Logarajah

collaborators

2 papers

stat.ML2026

On the Optimisation Landscape of Overparameterised Weighted MMD

Tharrshann Jayan Logarajah, Jeremias Knoblauch, Louis Sharrock

We study the optimisation landscape of the maximum mean discrepancy (MMD) over weighted atomic measures. For the one-dimensional Gaussian kernel, we show that, for any compactly su…

cs.CC2026

Parameterized Complexity of $L_{p}$ -Lipschitz Constants for Input Convex Neural Networks and $L_{p}$ -Norm Maximization over Zonotopes

Aritra Das, Vincent Froese, Moritz Grillo +6

Lipschitz constants are a standard way to quantify the sensitivity of neural networks to small input perturbations, but computing them is difficult even for shallow ReLU networks.…

On the Optimisation Landscape of Overparameterised Weighted MMD

Parameterized Complexity of Lp​-Lipschitz Constants for Input Convex Neural Networks and Lp​-Norm Maximization over Zonotopes

Parameterized Complexity of $L_{p}$ -Lipschitz Constants for Input Convex Neural Networks and $L_{p}$ -Norm Maximization over Zonotopes