Sampling from Mixture Distributions Based on Regime-Switching Diffusions
It is proposed to use stochastic differential equations with state-dependent switching 4 rates (SDEwS) for sampling from finite mixture distributions. An Euler scheme with constant time 5 step for SDEwS is considered. It is shown that the scheme converges with order one in weak sense 6 and also in the ergodic limit. Numerical experiments illustrate the use of SDEwS for sampling from 7 mixture distributions and confirm the theoretical results. 8 Key words. Stochastic differential equations with switching, hybrid switching diffusions, finite 9 mixture distributions, ergodic limits, sampling, weak numerical schemes.
Authors
- M. V. Tretyakov (ORCID: https://orcid.org/0000-0002-7929-9046)
Institutions
- University of Nottingham (GB)
Publication Details
- Journal
- SIAM Journal on Scientific Computing
- Published
- 2025-05-06
- DOI
- https://doi.org/10.1137/24m1677113
- Primary Topic
- Markov Chains and Monte Carlo Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Engineering and Physical Sciences Research Council