AI RESEARCH
Thinned Mean Field Langevin Dynamics
arXiv CS.LG
•
ArXi:2605.28589v1 Announce Type: new Several important learning tasks can be formulated as minimizing an entropy-regularized objective over an appropriate space of probability distributions. Mean-field Langevin dynamics (MFLD) facilitate computation in this general context, casting the minimizer as the invariant distribution of a McKean--Vlaso process, which can be numerically discretized using $N$ particles and thus simulated. However, simulating this interacting particle system has computational complexity of order $N^2