Efficient, multimodal, and derivative-free bayesian inference with Fisher–Rao gradient flows
In this paper, we study efficient approximate sampling for probability distributions known up
to normalization constants. We specifically focus on a problem class arising in Bayesian …
to normalization constants. We specifically focus on a problem class arising in Bayesian …
Deterministic Fokker-Planck Transport--With Applications to Sampling, Variational Inference, Kernel Mean Embeddings & Sequential Monte Carlo
I Klebanov - arXiv preprint arXiv:2410.18993, 2024 - arxiv.org
The Fokker-Planck equation can be reformulated as a continuity equation, which naturally
suggests using the associated velocity field in particle flow methods. While the resulting …
suggests using the associated velocity field in particle flow methods. While the resulting …
Transport Quasi-Monte Carlo
S Liu - arXiv preprint arXiv:2412.16416, 2024 - arxiv.org
Quasi-Monte Carlo (QMC) is a powerful method for evaluating high-dimensional integrals.
However, its use is typically limited to distributions where direct sampling is straightforward …
However, its use is typically limited to distributions where direct sampling is straightforward …
Distributed Lattice Kalman Filtering
S Li, Z Li, Z Zhang, P Liu, J Cui - 2023 China Automation …, 2023 - ieeexplore.ieee.org
The traditional single target real-time positioning accuracy is low and the multi-target
centralized positioning requires information fusion center and large communication volume …
centralized positioning requires information fusion center and large communication volume …