带Fisher信息正则化的平均场优化问题
Mean Field Optimization Problem Regularized by Fisher Information
AI总结:
该研究引入Fisher信息作为正则项,将正则化平均场优化问题与平均场薛定谔动力学关联,用能量耗散法证明其边缘分布指数收敛到唯一极小值,还提出蒙特卡洛采样方法,为神经网络训练分析等场景提供理论与算法支撑。
摘要:
近年来,平均场优化研究日益受到关注,这尤其源于其在神经网络训练分析中的作用。本文通过添加Fisher信息作为正则项,将带正则化的平均场优化问题与所谓的平均场薛定谔动力学(mean field Schrodinger dynamics)关联起来。我们提出了一种能量耗散方法,证明平均场薛定谔动力学的边缘分布会以指数速度收敛到该正则化优化问题的唯一极小值点。值得注意的是,平均场薛定谔动力学被证明是概率测度空间上关于相对熵的梯度流。最后,我们提出了一种蒙特卡洛方法来对平均场薛定谔动力学的边缘分布进行采样。
英文摘要:
Recently there is a rising interest in the research of mean field optimization, in particular because of its role in analyzing the training of neural networks. In this paper by adding the Fisher Information as the regularizer, we relate the regularized mean field optimization problem to a so-called mean field Schrodinger dynamics. We develop an energy-dissipation method to show that the marginal distributions of the mean field Schrodinger dynamics converge exponentially quickly towards the unique minimizer of the regularized optimization problem. Remarkably, the mean field Schrodinger dynamics is proved to be a gradient flow on the probability measure space with respect to the relative entropy. Finally we propose a Monte Carlo method to sample the marginal distributions of the mean field Schrodinger dynamics.
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。