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
  • [31] Markov Chain Monte Carlo Methods in Financial Econometrics
    Michael Verhofen
    Financial Markets and Portfolio Management, 2005, 19 (4): : 397 - 405
  • [32] Financial Monte Carlo Simulation on Architecturally Diverse Systems
    Singla, Naveen
    Hall, Michael
    Shands, Berkley
    Chamberlain, Roger D.
    2008 WORKSHOP ON HIGH PERFORMANCE COMPUTATIONAL FINANCE, 2008, : 21 - +
  • [33] Collective Monte Carlo updates through tensor network renormalization
    Frias-Perez, Miguel
    Marien, Michael
    Perez-Garcia, David
    Banuls, Mari Carmen
    Iblisdir, Sofyan
    SCIPOST PHYSICS, 2023, 14 (05):
  • [34] Towards overcoming the Monte Carlo sign problem with tensor networks
    Banuls, Mari Carmen
    Cichy, Krzysztof
    Cirac, J. Ignacio
    Jansen, Karl
    Kuehn, Stefan
    Saito, Hana
    XIITH QUARK CONFINEMENT AND THE HADRON SPECTRUM, 2017, 137
  • [35] Cyclone - Monte Carlo Data Processing and Visualization
    Hay, Stewart
    Hughes, Carl
    Taylor, Peter
    Proceedings of the Nuclear Criticality Safety Division Topical Meeting, NCSD 2022 - Embedded with the 2022 ANS Annual Meeting, 2022, : 10 - 13
  • [36] Mesoscale Monte Carlo simulation of photoresist processing
    Schmid, GM
    Stewart, MD
    Burns, SD
    Willson, CG
    JOURNAL OF THE ELECTROCHEMICAL SOCIETY, 2004, 151 (02) : G155 - G161
  • [37] Large-scale simulations on multiple Graphics Processing Units (GPUs) for the direct simulation Monte Carlo method
    Su, C. -C.
    Smith, M. R.
    Kuo, F. -A.
    Wu, J. -S.
    Hsieh, C. -W.
    Tseng, K. -C.
    JOURNAL OF COMPUTATIONAL PHYSICS, 2012, 231 (23) : 7932 - 7958
  • [38] Monte Carlo-based fluorescence molecular tomography reconstruction method accelerated by a cluster of graphic processing units
    Quan, Guotao
    Gong, Hui
    Deng, Yong
    Fu, Jianwei
    Luo, Qingming
    JOURNAL OF BIOMEDICAL OPTICS, 2011, 16 (02)
  • [39] Monte Carlo Simulation of Photon Migration in 3D Turbid Media Accelerated by Graphics Processing Units
    Fang, Qianqian
    Boas, David A.
    OPTICS EXPRESS, 2009, 17 (22): : 20178 - 20190
  • [40] Tunable, Mixed-Resolution Modeling Using Library-Based Monte Carlo and Graphics Processing Units
    Mamonov, Artem B.
    Lettieri, Steven
    Ding, Ying
    Sarver, Jessica L.
    Palli, Rohith
    Cunningham, Timothy F.
    Saxena, Sunil
    Zuckerman, Daniel M.
    JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2012, 8 (08) : 2921 - 2929