英文标题：
《Tensor Processing Units for Financial Monte Carlo》
---
作者：
Francois Belletti, Davis King, Kun Yang, Roland Nelet, Yusef Shafi,
  Yi-Fan Chen, John Anderson
---
最新提交年份：
2020
---
英文摘要：
  Monte Carlo methods are critical to many routines in quantitative finance such as derivatives pricing, hedging and risk metrics. Unfortunately, Monte Carlo methods are very computationally expensive when it comes to running simulations in high-dimensional state spaces where they are still a method of choice in the financial industry. Recently, Tensor Processing Units (TPUs) have provided considerable speedups and decreased the cost of running Stochastic Gradient Descent (SGD) in Deep Learning. After highlighting computational similarities between training neural networks with SGD and simulating stochastic processes, we ask in the present paper whether TPUs are accurate, fast and simple enough to use for financial Monte Carlo. Through a theoretical reminder of the key properties of such methods and thorough empirical experiments we examine the fitness of TPUs for option pricing, hedging and risk metrics computation. In particular we demonstrate that, in spite of the use of mixed precision, TPUs still provide accurate estimators which are fast to compute when compared to GPUs. We also show that the Tensorflow programming model for TPUs is elegant, expressive and simplifies automated differentiation.
---
中文摘要：
蒙特卡罗方法对定量金融中的许多常规程序至关重要，如衍生工具定价、对冲和风险度量。不幸的是，蒙特卡罗方法在高维状态空间中运行模拟时，计算成本非常高，在金融行业中，蒙特卡罗方法仍然是一种首选方法。最近，张量处理单元（TPU）提供了相当大的加速，并降低了在深度学习中运行随机梯度下降（SGD）的成本。在强调了用SGD训练神经网络和模拟随机过程之间的计算相似性之后，我们在本文中询问TPU是否足够准确、快速和简单，可以用于金融蒙特卡罗。通过对这些方法关键特性的理论提醒和深入的实证实验，我们检验了TPU在期权定价、对冲和风险度量计算方面的适用性。特别是，我们证明，尽管使用了混合精度，TPU仍然提供了准确的估计量，与GPU相比，计算速度更快。我们还表明，TPU的Tensorflow编程模型优雅、富有表现力，并简化了自动区分。
---
分类信息：

一级分类：Computer Science        计算机科学
二级分类：Distributed, Parallel, and Cluster Computing        分布式、并行和集群计算
分类描述：Covers fault-tolerance, distributed algorithms, stabilility, parallel computation, and cluster computing. Roughly includes material in ACM Subject Classes C.1.2, C.1.4, C.2.4, D.1.3, D.4.5, D.4.7, E.1.
包括容错、分布式算法、稳定性、并行计算和集群计算。大致包括ACM学科类C.1.2、C.1.4、C.2.4、D.1.3、D.4.5、D.4.7、E.1中的材料。
--
一级分类：Quantitative Finance        数量金融学
二级分类：Computational Finance        计算金融学
分类描述：Computational methods, including Monte Carlo, PDE, lattice and other numerical methods with applications to financial modeling
计算方法，包括蒙特卡罗，偏微分方程，格子和其他数值方法，并应用于金融建模
--
一级分类：Statistics        统计学
二级分类：Computation        计算
分类描述：Algorithms, Simulation, Visualization
算法、模拟、可视化
--

---
PDF下载：
-->