Solving differential equations with neural networks: Applications to the calculation of cosmological phase transitions

Abstract

Starting from the observation that artificial neural networks are uniquely suited to solving optimisation problems, and most physics problems can be cast as an optimisation task, we introduce a novel way of finding a numerical solution to wide classes of differential equations. We find our approach to be very flexible and stable without relying on trial solutions, and applicable to ordinary, partial and coupled differential equations. We apply our method to the calculation of tunnelling profiles for cosmological phase transitions, which is a problem of relevance for baryogenesis and stochastic gravitational wave spectra. Comparing our solutions with publicly available codes which use numerical methods optimised for the calculation of tunnelling profiles, we find our approach to provide at least as accurate results as these dedicated differential equation solvers, and for some parameter choices even more accurate and reliable solutions. In particular, we compare the neural network approach with two publicly available profile solvers, \texttt{CosmoTransitions} and \texttt{BubbleProfiler}, and give explicit examples where the neural network approach finds the correct solution while dedicated solvers do not. We point out that this approach of using artificial neural networks to solve equations is viable for any problem that can be cast into the form $\mathcal{F}(\vec{x})=0$, and is thus applicable to various other problems in perturbative and non-perturbative quantum field theory.

12 pages, 9 figures. V2: Typo fixes, title changed, agrees with version published in Phys. Rev. D

References in corpus (12)

• Singlet Higgs Phenomenology and the Electroweak Phase Transition
• Gravitational Waves from Phase Transitions at the Electroweak Scale and Beyond
• Sterile neutrinos, dark matter, and the pulsar velocities in models with a Higgs singlet
• Classification without labels: Learning from mixed samples in high energy physics
• A unified explanation for dark matter and electroweak baryogenesis with direct detection and gravitational wave signatures
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Electroweak Phase Transition and Baryogenesis in the nMSSM
• Efficient numerical solution to vacuum decay with many fields
• Numerical Approach to Multi Dimensional Phase Transitions
• Semi-analytic techniques for calculating bubble wall profiles
• Constrained potential method for false vacuum decays
• Double-charming Higgs identification using machine-learning assisted jet shapes

Cited by in corpus (4)

• Elvet -- a neural network-based differential equation and variational problem solver
• Machine Learning Etudes in Conformal Field Theories
• The Emergence of Electroweak Skyrmions through Higgs Bosons
• Unsupervised Learning of Solutions to Differential Equations with Generative Adversarial Networks