Code Monkey home page Code Monkey logo

juliusberner / deep_kolmogorov Goto Github PK

View Code? Open in Web Editor NEW
22.0 4.0 9.0 692.21 MB

Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning (NeurIPS 2020)

Home Page: https://arxiv.org/abs/2011.04602

License: MIT License

Dockerfile 0.41% Python 92.67% Jupyter Notebook 6.92%
deep-learning partial-differential-equations numerical-methods neurips-2020 pytorch ray-tune neural-network scientific-machine-learning

deep_kolmogorov's People

Contributors

juliusberner avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

deep_kolmogorov's Issues

How long to reproduce the result of Basket option?

Dear authors @juliusberner ,

Very nice work. Thank you for the code.

We are able to reproduce your result for the Black-Scholes model (Table 1), heat equation with paraboloid initial condition (Table 3), and Gaussian initial condition (Table 4). However, we have a problem with the Basket option (Table 2). The time for gradient step 4k is not within 811s as the table suggested. In fact, we didn't even get any results even though we kept the code run for 12 hours.

We guess the main reason perhaps due to the two inner loops in that the code for the simulation of the solution (

for t, x, sigma, mu, K in zip(
)
Do you think we can remove this part and make it parallel?

I wonder if you already save some of the simulated data that we could directly use. Thank you very much!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.