Generative Nested Sampling of Atomistic Thermodynamic Landscapes
arXiv:2609.03193
2026
Sampling
2 ideas extracted · analyzed Sep 4, 2026
What the math gives to ML
The paper offers a constructive replacement for expensive constrained MCMC in nested sampling: a single normalizing flow conditioned on the current likelihood or energy bound is trained from a sliding window of recent live points, then used for parallel importance-weighted proposals and rejection resampling. Its transferable asset is self-consistent amortized sampling of changing constrained ensembles without requiring a pre-existing training set or structured prior. For neural networks, the strongest applications are accelerating exploration of Bayesian neural-network posteriors, neural energy landscapes, diffusion latents, or world-model state distributions while monitoring flow efficiency as a quantitative diagnostic of multimodality and target drift.
Ideas from this paper
Unverified
2026
Use a conditional normalizing flow to replace inner-loop MCMC when sampling states or parameters under progressively tighter neural energy or likelihood constraints. The flow is trained online from recent live sets, and proposals are corrected by importance weighting and resampling, so flow bias does not directly corrupt the nested estimate.
Useful8/10
Difficulty6/10
Novelty6/10
Unverified
2026
Turn constrained-flow generation efficiency into an online diagnostic and controller for neural sampling. When the target ensemble changes faster than the flow can track or becomes internally complex, automatically shorten the training window, increase flow updates, or fall back to local MCMC instead of silently accepting biased or highly correlated samples.
Useful7/10
Difficulty5/10
Novelty7/10