Skip to main content
Search

# Sequential Monte Carlo

3 related articles

Subscribe to updates
  1. arXiv

    Standard-siren cosmology stops restarting from the prior: ASPIRE reuses old posteriors for a roughly 29-fold speed-up in a dark-siren case

    Standard-siren cosmology jointly infers cosmological and compact-binary population parameters, and each change of galaxy catalogue, mass model or event set has usually meant a full reanalysis from the prior. ASPIRE fits a normalising flow to existing posterior samples and anneals them with sequential Monte Carlo toward the posterior under a new hypothesis, recovering posteriors consistent with nested sampling on GWTC-5.0 dark-siren cases while still estimating Bayesian evidence. Adding GLADE+ galaxy-catalogue information to a spectral-siren result cut sampling time from 134.4 hours to 4.6 hours.

    Alexander Papadopoulos（First author）
    ASPIREStandard Siren CosmologySequential Monte CarloNormalizing Flows
  2. arXiv

    Subsurface flow data assimilation gets adaptive-tempered sequential Monte Carlo: posteriors match reference MCMC on four synthetic truths, with 2.5–7.0× single-GPU speedups

    Geological uncertainty in subsurface flow systems is often hierarchical: a set of geological metaparameters controls overall statistics while cell-by-cell property fields vary, and both must be estimated from observations. An adaptive-tempered sequential Monte Carlo method estimates metaparameters and Gaussian latent variables jointly within one likelihood framework, with surrogate models supplying all forward evaluations. Across four synthetic true models, its posterior metaparameter distributions and flow predictions agree closely with reference MCMC results, while single-GPU data assimilation is 2.5–7.0 times faster and needs fewer function evaluations.

    Stanford University
    Wenchao Teng（First author）
    Sequential Monte CarloData AssimilationMarkov Chain Monte CarloLatent Diffusion ModelPrincipal Component Analysis
  3. arXiv

    Power sampling fails to converge at real compute budgets, and simple Best-of-N matches its reasoning gains

    MCMC and SMC samplers for the power distribution fail to converge under realistic compute budgets, and their reasoning gains are largely recreated by simple Best-of-N selection; Power-RLOO, which fine-tunes directly toward the power distribution, helps only when the base model is already aligned with the task.

    Lancaster University
    Abiel Malkani Talwar（First author）
    Power-RLOOPower SamplingSequential Monte CarloMarkov Chain Monte CarloTraining-Free LLM Reasoning

You’re all caught up