Newton Raphson Emulation Network for Highly Efficient Computation of Numerous Implied Volatilities

TL;DR

This paper introduces a neural network emulation of the Newton-Raphson method for rapid computation of implied volatilities, achieving up to 1,000 times speedup over traditional algorithms.

Contribution

The authors develop a neural network-based emulation of the Newton-Raphson method optimized with TensorRT, significantly accelerating implied volatility calculations.

Findings

Emulation network is up to 1,000 times faster than SciPy's NR implementation.

The approach maintains high accuracy in implied volatility estimation.

Optimization with TensorRT enhances inference speed substantially.

Abstract

In finance, implied volatility is an important indicator that reflects the market situation immediately. Many practitioners estimate volatility using iteration methods, such as the Newton--Raphson (NR) method. However, if numerous implied volatilities must be computed frequently, the iteration methods easily reach the processing speed limit. Therefore, we emulate the NR method as a network using PyTorch, a well-known deep learning package, and optimize the network further using TensorRT, a package for optimizing deep learning models. Comparing the optimized emulation method with the NR function in SciPy, a popular implementation of the NR method, we demonstrate that the emulation network is up to 1,000 times faster than the benchmark function.