Quenched Ensemble Sampling

• URL: http://arxiv.org/abs/2609.15894v1
• Date: Mon, 14 Sep 2026 17:16:07 GMT
• Title: Quenched Ensemble Sampling
• Abstract summary: We introduce Quenched Ensemble Sampling, which generalises the hard constraint to a family of repulsive potentials at the energy boundary.<n>We demonstrate on synthetic models of phase transitions that our method estimates the marginal likelihood and draws posterior samples across a first-order transition.<n>In a high-dimensional continuous lattice field theory, we show that this method traverses a first-order transition and estimates the partition function.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Some of the sharpest challenges in sampling from the energy functions of physical systems arise at phase transitions, where the density of states changes abruptly and many sampling algorithms stall. Nested sampling is a particle method that traverses the density of states under a hard energy constraint and is known to be robust to such transitions, but its application in high dimension is limited by the difficulty of sampling under that constraint. In this work we introduce Quenched Ensemble Sampling, which generalises the hard constraint to a family of repulsive potentials at the energy boundary. This preserves the quenched path of monotonically decreasing energy while making the constrained target amenable to scalable gradient-based kernels. We demonstrate on synthetic models of phase transitions that our method estimates the marginal likelihood and draws posterior samples across a first-order transition where popular alternatives such as tempering fail. We apply the procedure to marginal likelihood estimation in Bayesian neural networks, enabling model comparison between network architectures. Finally, in a high-dimensional continuous lattice field theory, we show that this method traverses a first-order transition and estimates the partition function.

Related papers

• Measurement-induced state transitions across the fluxonium qubit landscape [73.92964306525622]
  We study measurement-induced state transitions in the fluxonium qubit over a wide range of parameters.<n>We find that lighter fluxoniums are less susceptible to these state transitions when compared to their heavier counterparts.<n>We attribute this effect to the combination of lower density of multi-photon resonances, a smaller requisite coupling for a given dispersive shift, and a more harmonic-like structure of the charge operator.
  arXiv  Detail & Related papers  (2026-04-09T17:53:41Z)
• Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds [0.5729426778193398]
  We study the emergence of multi-step reasoning in deep Transformer language models through a geometric and statistical-physics lens.<n>We formalize the forward pass as a discrete coarse-graining map and relate the appearance of stable "concept basins" to fixed points of this renormalization-like dynamics.<n>The resulting low-entropy regime is characterized by a spectral tail collapse and by the formation of transient, reusable object-like structures in representation space.
  arXiv  Detail & Related papers  (2026-01-16T23:11:02Z)
• Functional Gradient Flows for Constrained Sampling [29.631753643887237]
  We propose a new functional gradient ParVI method for constrained sampling, called constrained functional gradient flow (CFG) We also present novel numerical strategies to handle the boundary integral term arising from the domain constraints.
  arXiv  Detail & Related papers  (2024-10-30T16:20:48Z)
• Exact solution of the infinite-range dissipative transverse-field Ising model [0.0]
  We present an exact solution for the steady state of the transverse-field Ising model in the limit of infinite-range interactions. Our solution holds despite the lack of any collective spin symmetry or even permutation symmetry. It allows us to investigate first- and second-order dissipative phase transitions, driven-dissipative criticality, and captures the emergence of a surprising "spin blockade" phenomenon.
  arXiv  Detail & Related papers  (2023-07-13T17:59:23Z)
• Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers [90.45898746733397]
  We develop a framework for non-asymptotic analysis of deterministic samplers used for diffusion generative modeling. We show that one step along the probability flow ODE can be expressed as two steps: 1) a restoration step that runs ascent on the conditional log-likelihood at some infinitesimally previous time, and 2) a degradation step that runs the forward process using noise pointing back towards the current gradient.
  arXiv  Detail & Related papers  (2023-03-06T18:59:19Z)
• Aspects of scaling and scalability for flow-based sampling of lattice QCD [137.23107300589385]
  Recent applications of machine-learned normalizing flows to sampling in lattice field theory suggest that such methods may be able to mitigate critical slowing down and topological freezing. It remains to be determined whether they can be applied to state-of-the-art lattice quantum chromodynamics calculations.
  arXiv  Detail & Related papers  (2022-11-14T17:07:37Z)
• Sampling with Mollified Interaction Energy Descent [57.00583139477843]
  We present a new optimization-based method for sampling called mollified interaction energy descent (MIED) MIED minimizes a new class of energies on probability measures called mollified interaction energies (MIEs) We show experimentally that for unconstrained sampling problems our algorithm performs on par with existing particle-based algorithms like SVGD.
  arXiv  Detail & Related papers  (2022-10-24T16:54:18Z)
• Non-Hermitian topological quantum states in a reservoir-engineered transmon chain [0.0]
  We show that a non-Hermitian quantum phase can be realized in a reservoir-engineered transmon chain. We show that genuine quantum effects are observable in this system via robust and slowly decaying long-range quantum entanglement of the topological end modes.
  arXiv  Detail & Related papers  (2022-10-06T15:21:21Z)
• Conditioning Normalizing Flows for Rare Event Sampling [61.005334495264194]
  We propose a transition path sampling scheme based on neural-network generated configurations. We show that this approach enables the resolution of both the thermodynamics and kinetics of the transition region.
  arXiv  Detail & Related papers  (2022-07-29T07:56:10Z)
• Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC [83.48593305367523]
  Hybrid Monte Carlo is a powerful Markov Chain Monte Carlo method for sampling from complex continuous distributions. We introduce a new approach based on augmenting Monte Carlo methods with SurVAE Flows to sample from discrete distributions. We demonstrate the efficacy of our algorithm on a range of examples from statistics, computational physics and machine learning, and observe improvements compared to alternative algorithms.
  arXiv  Detail & Related papers  (2021-02-04T02:21:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.