Tensor Processing Units for Financial Monte Carlo

被引:0
|
作者
Belletti, Francois [1 ]
King, Davis [1 ]
Yang, Kun [1 ]
Nelet, Roland [1 ]
Shafi, Yusef [1 ]
Shen, Yi-Fan [1 ]
Anderson, John [1 ]
机构
[1] Google Res, Mountain View, CA 94043 USA
关键词
DERIVATIVES; SIMULATION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
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.
引用
收藏
页码:12 / 23
页数:12
相关论文
共 50 条
  • [1] Quantum Monte Carlo on graphical processing units
    Anderson, Amos G.
    Goddard, William A., III
    Schroeder, Peter
    COMPUTER PHYSICS COMMUNICATIONS, 2007, 177 (03) : 298 - 306
  • [2] Monte Carlo Option Pricing With Graphics Processing Units
    Nord, Fredrik
    Laure, Erwin
    APPLICATIONS, TOOLS AND TECHNIQUES ON THE ROAD TO EXASCALE COMPUTING, 2012, 22 : 143 - 150
  • [3] The Metropolis Monte Carlo method with CUDA enabled Graphic Processing Units
    Hall, Clifford
    Ji, Weixiao
    Blaisten-Barojas, Estela
    JOURNAL OF COMPUTATIONAL PHYSICS, 2014, 258 : 871 - 879
  • [4] Monte Carlo MP2 on Many Graphical Processing Units
    Doran, Alexander E.
    Hirata, So
    JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2016, 12 (10) : 4821 - 4832
  • [5] Pricing derivatives on graphics processing units using Monte Carlo simulation
    Abbas-Turki, L. A.
    Vialle, S.
    Lapeyre, B.
    Mercier, P.
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2014, 26 (09): : 1679 - 1697
  • [6] Molecular Monte Carlo Simulations Using Graphics Processing Units: To Waste Recycle or Not?
    Kim, Jihan
    Rodgers, Jocelyn M.
    Athenes, Manuel
    Smit, Berend
    JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2011, 7 (10) : 3208 - 3222
  • [7] Phaseless Auxiliary-Field Quantum Monte Carlo on Graphical Processing Units
    Shee, James
    Arthur, Evan J.
    Zhang, Shiwei
    Reichman, David R.
    Friesner, Richard A.
    JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2018, 14 (08) : 4109 - 4121
  • [8] Monte Carlo simulation in financial engineering
    Chen, Nan
    Hong, L. Jeff
    PROCEEDINGS OF THE 2007 WINTER SIMULATION CONFERENCE, VOLS 1-5, 2007, : 898 - +
  • [9] Monte Carlo methods in financial engineering
    Cont, R
    QUANTITATIVE FINANCE, 2004, 4 (04) : C46 - C47
  • [10] Monte Carlo Simulation in Financial Modeling
    Simsek, Koray D.
    JOURNAL OF PORTFOLIO MANAGEMENT, 2023, 49 (09): : 178 - 188