跳到正文
arXiv cs.AI· Michael Chertkov·· 10 小时前AI 评分22

路径积分扩散(PID)如何决定有限自旋玻璃的宏观选择

How Path Integral Diffusion Decides a Finite Spin Glass

AI 导读

研究指出,从点源出发的各向同性路径积分扩散(PID)模型等价于时间变换的高斯随机局部化,且任意信噪比调度都可由 PID 协议实现,因此连续时间生成器"决定什么"不依赖协议,协议只决定何时与何种代价。

正文 · 原文

View PDF HTML (experimental)

Abstract:When an AI diffusion-type generator samples a frustrated spin glass, which macroscopic alternatives does it decide first, and when? We study this for bridge-diffusion models of the Path Integral Diffusion (PID) type started from a point source. We show that every isotropic PID is a time-changed Gaussian stochastic localization, and conversely every signal-to-noise schedule is realized by a PID protocol. What a continuous-time generator decides therefore does not depend on the protocol, which only sets when and at what cost. We describe the generator's state by its partial commitments: the probabilities it assigns, at each moment, to nested classes of configurations fixed by the target. The partial commitments are martingales that move only along class contrasts. Their ensemble average gives the information about each level at an exact rate set by squared magnetization contrasts. In the balanced, effectively binary approximation, a split reaches half of its class information near \gamma=1.044/\lambda_P, where \lambda_P is the leading eigenvalue of the parent covariance. The theory is applied to Bethe-lattice and Sherrington--Kirkpatrick (SK) glasses with up to 24 spins. It is observed generically that a trajectory first shifts its weight to one of the two mirror halves of the zero-field measure and then to the glassy classes inside it. These classes appear near the glass transition, keep their identity on cooling and are absent in a ferromagnet on the same graphs. Sparse (Bethe) and dense (SK) glasses differ in how often and how strongly such classes exist, not in how trajectories commit to them. For a generator that takes finitely many steps, the protocol matters through the late, local stage rather than the macroscopic decisions. Sampled posteriors at N=32,64 and small trained denoisers show the same sequence.
Comments: 47 pages, 18 figures
Subjects: Disordered Systems and Neural Networks (cond-mat.dis-nn); Statistical Mechanics (cond-mat.stat-mech); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
Cite as: arXiv:2611.11826 [cond-mat.dis-nn]
  (or arXiv:2611.11826v2 [cond-mat.dis-nn] for this version)
  https://doi.org/10.48550/arXiv.2611.11826

arXiv-issued DOI via DataCite

Submission history

From: Michael Chertkov [view email]
[v1] Mon, 9 Nov 2026 03:44:59 UTC (792 KB)
[v2] Tue, 17 Nov 2026 23:00:27 UTC (854 KB)

来源:arXiv cs.AI · arxiv.org