离散随机动力学模型中参数推断的梯度估计器
Gradient estimators for parameter inference in discrete stochastic kinetic models
AI总结:
针对Gillespie随机模拟算法不可微的问题,采用三种机器学习梯度估计器(Gumbel-Softmax直通、得分函数、替代路径)实现参数梯度计算,并在弛豫和振荡动力学系统中验证了其有效性。
摘要:
随机动力学模型在物理学中无处不在,但从实验数据推断其参数仍然具有挑战性。对于确定性模型,参数推断通常依赖于梯度,这些梯度可以通过自动微分(AD)高效获得。然而,AD不能直接应用于Gillespie随机模拟算法(SSA),因为从离散反应集合中采样引入了不可微操作。在这项工作中,我们采用三种来自机器学习的梯度估计器用于Gillespie SSA:Gumbel-Softmax直通(GS-ST)估计器、得分函数估计器和替代路径估计器。我们使用这些估计器来评估稳态和时间依赖可观测量的梯度,并在具有弛豫动力学(双分子结合)和振荡动力学(抑制子)的代表性生物物理系统中比较它们的性能。我们发现GS-ST估计器通常产生表现良好的梯度估计,但在具有挑战性的参数区域中表现出发散的方差,这可能导致参数推断失败。在这些情况下,其他估计器提供更稳健、方差更低的梯度。我们的结果表明,基于梯度的参数推断可以有效地与Gillespie SSA结合,不同的估计器提供互补的优势。
英文摘要:
Stochastic kinetic models are ubiquitous in physics, yet inferring their parameters from experimental data remains challenging. For deterministic models, parameter inference often relies on gradients, which can be obtained efficiently through automatic differentiation (AD). However, AD cannot be applied directly to the Gillespie stochastic simulation algorithm (SSA), since sampling from a discrete set of reactions introduces non-differentiable operations. In this work, we adopt three gradient estimators from machine learning for the Gillespie SSA: the Gumbel-Softmax Straight-Through (GS-ST) estimator, the Score Function estimator, and the Alternative Path estimator. We use the estimators to evaluate gradients of steady-state and time-dependent observables, and compare their performance in representative biophysical systems with relaxation dynamics (bimolecular association) and oscillatory dynamics (repressilator). We find that the GS-ST estimator generally yields well-behaved gradient estimates, but exhibits diverging variance in challenging parameter regimes, which can cause parameter inference to fail. In these cases, other estimators provide more robust, lower variance gradients. Our results demonstrate that gradient-based parameter inference can be effectively combined with the Gillespie SSA, with different estimators offering complementary advantages.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。