3 papers
cs.LG2026
Parameter-Level Attribution of Symmetry in Trained Networks Though Parameter-Wise Functional Sensitivity
Alan Muriithi, Vedanta Thapar, Torben Berndt
When a network has learned a function with a known symmetry, can that symmetry be moved through the parametrisation---is there a motion in parameter space realising the group actio…
cs.LG2026
Machine Learning Hamiltonian Dynamical Systems with Sparse and Noisy Data
Vedanta Thapar, Abhinav Gupta
Machine learning has become a powerful tool for discovering governing laws of dynamical systems from data. However, most existing approaches degrade severely when observations are…
cs.SI2025
Embedding networks with the random walk first return time distribution
Vedanta Thapar, Renaud Lambiotte, George T. Cantwell
We propose the first return time distribution (FRTD) of a random walk as an interpretable and mathematically grounded node embedding. The FRTD assigns a probability mass function t…