The paper introduces a data-driven effective model for stochastic chemical reaction networks that bypasses the high computational cost of the Stochastic Simulation Algorithm (SSA). By approximating the finite-time transition kernel of the SSA-induced continuous-time Markov chain with a generative machine learning model, the method operates on a user-defined coarse time step independent of microscopic reaction events. Using a conditional normalizing flow as the stochastic propagator, the trained model recursively generates statistically consistent trajectories, achieving significant computational savings while maintaining accuracy, as demonstrated through numerous numerical examples.
By Yuan Chen, Weize Mao, Dongbin Xiu
arXiv:2608. 06259v1 Announce Type: new Abstract: Reaction yield prediction remains challenging because labeled data are scarce and reaction space is both combinatorially large and sparsely populated, limiting the generalization of existing reaction representations.
By Yiting Zheng, Cheng Fang, Anthony Donofrio, Haote Li
arXiv:2509.13267v3 Announce Type: replace-cross
Abstract: A discrete Bayesian network is a directed acyclic graph (DAG) consisting of categorical variables. Two popular approaches for DBN modeling in...
By Alexander Dombowsky, David B. Dunson
arXiv:2607. 12771v1 Announce Type: new Abstract: Reaction mechanisms consist of the step-by-step sequences of elementary reactions that explain chemical transformations.
By Xingyu Dang, Haocheng Tang, Junmei Wang, Yanjun Li
arXiv:2607. 19126v1 Announce Type: cross Abstract: Neural Markov Logic Networks (NMLNs) are a flexible neurosymbolic relational model.
By Peter Jung, Giuseppe Marra, Ondrej Kuzelka
Probabilistic inference in high-dimensional Bayesian networks is difficult because exact manipulation of the joint distribution scales exponentially with network size. We propose a decomposition framework based on directed convex subgraphs and introduce a minimal d-decomposition tree.