Howard Jessica N, Mandt Stephan, Whiteson Daniel, Yang Yibo
Department of Physics and Astronomy, UC Irvine, Irvine, CA, USA.
Department of Computer Science, UC Irvine, Irvine, CA, USA.
Sci Rep. 2022 May 9;12(1):7567. doi: 10.1038/s41598-022-10966-7.
In many scientific fields which rely on statistical inference, simulations are often used to map from theoretical models to experimental data, allowing scientists to test model predictions against experimental results. Experimental data is often reconstructed from indirect measurements causing the aggregate transformation from theoretical models to experimental data to be poorly-described analytically. Instead, numerical simulations are used at great computational cost. We introduce Optimal-Transport-based Unfolding and Simulation (OTUS), a fast simulator based on unsupervised machine-learning that is capable of predicting experimental data from theoretical models. Without the aid of current simulation information, OTUS trains a probabilistic autoencoder to transform directly between theoretical models and experimental data. Identifying the probabilistic autoencoder's latent space with the space of theoretical models causes the decoder network to become a fast, predictive simulator with the potential to replace current, computationally-costly simulators. Here, we provide proof-of-principle results on two particle physics examples, Z-boson and top-quark decays, but stress that OTUS can be widely applied to other fields.
在许多依赖统计推断的科学领域中，模拟常常被用于从理论模型映射到实验数据，使科学家能够根据实验结果检验模型预测。实验数据往往是通过间接测量重建的，这使得从理论模型到实验数据的整体转换难以用解析方法进行描述。相反，数值模拟需要耗费巨大的计算成本。我们引入了基于最优传输的展开与模拟（OTUS），这是一种基于无监督机器学习的快速模拟器，能够从理论模型预测实验数据。在无需当前模拟信息的情况下，OTUS训练一个概率自动编码器，以在理论模型和实验数据之间直接转换。将概率自动编码器的潜在空间与理论模型空间相识别，会使解码器网络成为一个快速的预测模拟器，有潜力取代当前计算成本高昂的模拟器。在此，我们在两个粒子物理示例（Z玻色子和顶夸克衰变）上提供了原理验证结果，但强调OTUS可广泛应用于其他领域。
