Machine learning · Scientific computing

Physics-Informed Neural Networks for Financial PDEs

Inverse-PDE experiments for recovering local-volatility surfaces under controlled noise.

Why

Local-volatility calibration is an inverse problem: infer a stable volatility surface from noisy observations while respecting the governing financial PDE.

Tech stack

  • Python
  • PyTorch
  • PINNs
  • Neural ODEs
  • Autograd

Key metrics

2–3 orders lower surface MSE
3 noise levels tested

What I built

  • Implemented inverse PINN and neural-adjoint solvers for Black-Scholes and Dupire constraints.
  • Built controlled experiments at 0%, 1%, and 5% noise with fixed evaluation grids.
  • Compared surface error, smoothness, training time, and stability against simpler baselines.

How it works

  1. Noisy option observations
  2. Neural volatility surface
  3. Autograd PDE residuals
  4. Boundary and data losses
  5. Recovered surface
  6. Baseline comparison

Evaluation

  • Use the same observations, grid, noise seed, and error calculation for every solver.
  • Report surface MSE with training time and failure behavior instead of treating fit alone as success.
Inverse-PDE experiment summary
MeasureResultBoundary
Surface MSE2–3 orders lowerAcross controlled 0%, 1%, and 5% noise settings
Recovered surfaceSmoother than simpler baselinesEvaluated on a fixed grid
Compute costHigher training timeAccuracy and stability came with a clear cost

Limitations

  • Results come from controlled synthetic-noise experiments, not live market calibration.
  • PINN training is slower and sensitive to loss weighting and optimization.
  • The public repository and full experiment artifact are not yet linked.

Links and reproducibility

  • Freeze the observation grid, noise seeds, solver settings, and evaluation grid before comparison.
  • Publish surface-error tables, training curves, runtime, and failed runs with the source.