Neural Networks with Asymptotics Control

In this webinar you will learn more about some of the advantages and use cases for applying machine learning, deep learning, and neural networks in mathematical finance.

Artificial Neural Networks (ANNs) have recently been proposed as accurate and fast approximators in various derivatives pricing applications. ANNs typically excel in fitting functions they approximate at the input parameters they are trained on, and often are quite good in interpolating between them. However, for standard ANNs, their extrapolation behavior – an important aspect for financial applications – cannot be controlled due to complex functional forms typically involved.

In this new research quantitative experts overcome this significant limitation and develop a new type of neural networks that incorporate large-value asymptotics, when known, allowing explicit control over extrapolation.

This new research, conducted in collaboration with Dr. Alexandre Antonov of Danske Bank and Dr. Vladimir Piterbarg of NatWest Markets, was presented live on Thursday, February 11th at 10 AM EST by Dr. Michael Konikov, Senior Vice President and Head of Quantitative Development at Numerix.

The session offers insights and commentary across several areas including:

  • Introduction to neural networks and their use in finance
  • Spline as a control variate matching asymptotics
  • Special constrained radial layer to fit residual
  • Numerical experiments
  • Conclusions

Featured Speakers


Want More from Numerix?

Subscribe to our mailing list to stay current on what we're doing and thinking at Numerix