arXiv · 1508.05865
Learning of couplings for random asymmetric kinetic Ising models revisited: random correlation matrices and learning curves
Abstract
We study analytically the performance of a recently proposed algorithm for learning the couplings of a random asymmetric kinetic Ising model from finite length trajectories of the spin dynamics. Our analysis shows the importance of the nontrivial equal time correlations between spins induced by the dynamics for the speed of learning. These correlations become more important as the spin's stochasticity is decreased. We also analyse the deviation of the estimation error from asymptotic optimality.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Ludovica Bachschmid-Romano, Manfred Opper. 2015-08-28. Learning of couplings for random asymmetric kinetic Ising models revisited: random correlation matrices and learning curves. https://doi.org/10.1088/1742-5468%2F2015%2F09%2Fp09016
Cite the original work for its findings. Save a collection to share your selection of sources.