cs.LGNov 18, 2026

Federated Learning of Car Aerodynamics Surrogates with Spectral Optimizers

Authors: Arman Bolatov, Nikolay Spitsyn, Daniil Medyakov, Vladimir Aletov, Dmitry Bylinkin, Martin Takáč, Aleksandr Beznosikov

Organizations: Basic Research of Artificial Intelligence Laboratory (BRAIn Lab) · Moscow Independent Research Institute of Artificial Intelligence (MIRAI) · Federated Learning Problems Laboratory · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · 

Abstract

Neural surrogates predict the aerodynamic forces on a car in seconds, compared with hours for a CFD simulation, but training them requires thousands of CFD simulations of different car designs, which car manufacturers keep proprietary. Federated learning allows several manufacturers to train a shared surrogate without exchanging data. We study which federated optimizer brings such a surrogate closest to one trained on pooled data. On DrivAerNet++, we train a Transolver surrogate across six clients that each hold cars of a single body type, and we compare three spectral optimizers, which orthogonalize the update of each weight matrix (FedMuon and two methods we propose, FedMARS-M and FedOLion), with three non-spectral ones (FedAvg, SCAFFOLD-Adam and FedLion), all tuned with the same protocol. FedMuon and FedMARS-M reach a drag error within 2% of centralized training with Muon, using two to four local epochs per round. The non-spectral methods perform best with sixteen local epochs, the largest number we tested, and still have a 17 to 37% higher drag error than FedMARS-M. We relate this gap to the low stable rank of the weight gradients, for which an orthogonalized step yields about twice the first-order decrease of a gradient step of the same spectral norm. Code: https://github.com/armanbolatov/fedmars_drivaernet

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Measuring and Improving Transfer of Neural Surrogates for Vehicle Aerodynamics

    Nov 18, 2026Favour Nerrise, Julian Busch, Gurpreet Singh Hora +3Neural Surrogate ModelingTransfer Learning

  2. Faster by Design: Interactive Aerodynamics via Neural Surrogates Trained on Expert-Validated CFD

    Apr 20, 2026Nicholas Thumiger, Andrea Bartezzaghi, Mattia Rigotti +5PDE Surrogate ModelingGraph Neural Operators