Logo
  • Getting started
  • Tutorials
  • Fitting code: n3fit
    • Methodology overview
    • n3fit runcard detailed guide
    • Hyperoptimization algorithm
  • Code for data: validphys
  • Storage of data and theory predictions
  • Theory
  • Chi square figures of merit
  • Contributing guidelines and tools
  • Releases and compatibility policy
  • Continuous integration and deployment
  • Servers
  • External codes
NNPDF
  • Fitting code: n3fit
  • View page source

Fitting code: n3fit

  • n3fit is the next generation fitting code for NNPDF developed by the N3PDF team [CCM19]

  • n3fit is responsible for fitting PDFs from NNPDF4.0 onwards.

  • The code is implemented in python using Keras and can run with Tensorflow (default) or pytorch (with the environment variable KERAS_BACKEND=torch).

  • The sections below are an overview of the n3fit design.

Important

If you just want to know how to run a fit using n3fit, head to How to run a PDF fit.

  • Methodology overview
    • Introduction
    • Neural network architecture
    • Preprocessing
    • Optimizer
    • Stopping algorithm
    • Positivity
    • Integrability
    • Feature Scaling
  • n3fit runcard detailed guide
    • Dataset selection
    • Monte Carlo replica data
    • Preprocessing
    • Network Architecture
    • Optimizer
    • Positivity
    • Integrability
    • Regularized covariance matrices
    • Inspecting and profiling the code
    • Running fits in parallel
    • Other options
  • Hyperoptimization algorithm
    • Motivation
    • K-folding cross-validation
    • Creating partitions
    • Interpretation of results
    • Implementation in n3fit
    • Implementation in validphys
    • Positivity and integrability
    • Practical Usage
    • Changing the hyperoptimization target
    • Restarting hyperoptimization runs
    • Running hyperoptimizations in parallel with MongoDB
Previous Next

© Copyright 2025, NNPDF collaboration.

Built with Sphinx using a theme provided by Read the Docs.