KT-MFLD thins the particle system in mean-field Langevin dynamics to O(N^{3/2}) complexity with convergence guarantees matching standard MFLD up to logarithmic factors.
arXiv preprint arXiv:2509.10393 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Predictive Bayesian inference posteriors concentrate onto a forward-model-dependent quantity and produce miscalibrated credible sets unless the predictive model contains the true data-generating process.
citing papers explorer
-
Thinned Mean Field Langevin Dynamics
KT-MFLD thins the particle system in mean-field Langevin dynamics to O(N^{3/2}) complexity with convergence guarantees matching standard MFLD up to logarithmic factors.
-
Concentration and Calibration in Predictive Bayesian Inference
Predictive Bayesian inference posteriors concentrate onto a forward-model-dependent quantity and produce miscalibrated credible sets unless the predictive model contains the true data-generating process.