Derives Wasserstein bounds and explicit hyperparameter tuning rules for annealed Langevin dynamics in compositional score-based SBI, proving Linhart et al. (2026) allows larger steps and fewer total steps than Geffner et al. (2023) in the Gaussian case.
hub Mixed citations
arXiv preprint arXiv:2508.12939 , year=
Mixed citation behavior. Most common role is background (60%).
17
Pith papers citing it
Background
60% of classified citations
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
Extends NPE to mixed discrete-continuous parameter spaces via a factorized inference network combining an autoregressive classifier and generative model, trained jointly to yield accurate calibrated posteriors.
Generative models for cosmological field-level inference can reproduce posterior means and cross-correlations yet fail to capture correct uncertainty geometry when validated against HMC reference samples.
GenSBI delivers JAX-native implementations of generative SBI methods with transformer backbones and reports near-ideal calibration scores on standard benchmarks.
SPIN performs bidirectional domain transfer in SBI to retain parameter mutual information from unlabeled real observations, improving real-world posterior inference under increasing misspecification.
A multimodal amortized neural posterior estimator trained on realistic simulations recovers DEB parameters accurately with calibrated uncertainties on held-out tests.
FLUID uses a recurrent encoder to create a fixed-size summary of observations, then learns coupled forward and backward flows to approximate filtering distributions and recover smoothing paths for nonlinear dynamics, with support for extrapolation.
A neural posterior estimator trained on simulated LISA foreground spectra recovers galactic binary population parameters, including total number, with good accuracy in validation tests.
Auto-encoder compression of X-ray spectra with multi-round neural posterior estimation and likelihood-based importance sampling yields posteriors statistically indistinguishable from nested sampling at roughly 10x speedup.
Optimization Monte Carlo reformulates stochastic simulator inference as gradient-based deterministic optimization for faster, accurate posterior estimation in high-dimensional or challenging settings.
OpenSeisML curates public seismic surveys into a reproducible dataset for training generative models that produce multiple statistically consistent subsurface realizations to support uncertainty-aware seismic inversion.
Neural posterior estimation trained on GPU-simulated radar data enables calibrated probabilistic inversion of terrain parameters and transfers to real Mars radar profiles.
Amortized neural posterior estimation via simulation-based inference delivers 82x faster inference than MCMC for heat exchanger fouling and leakage diagnosis while maintaining comparable accuracy on synthetic data.
Simulation-based inference reliably extracts physical parameters from noisy spectra of analogue black holes.
NPE delivers millisecond-scale parameter inference for Li-ion batteries that matches or exceeds Bayesian calibration accuracy while adding local sensitivity interpretability, though with higher voltage prediction errors.
Simulation-based inference uses neural networks trained on simulations to enable parameter inference in cosmology and astrophysics where traditional likelihood calculations are intractable.
A synthesis of diffusion-based simulation-based inference methods that address model misspecification, irregular observations, and missing data in scientific applications.
citing papers explorer
No citing papers match the current filters.