cs.LGNov 17, 2026

Conformally Calibrated Adaptive Computation in Neural Operators

Authors: Abdul Qadir Ibrahim, Martin Burger, Abel Maviano Jonathan

Organizations: Deutsches Elektronen-Synchrotron DESY, Hamburg, Germany · Department of Information Engineering, Computer Science and Mathematics University of L’Aquila, L’Aquila, Italy

Abstract

Selecting less computation in a neural operator need not reduce inference time. We study this gap using conformal calibration to choose Fourier modes or channel width per input subject to a fixed error budget. A triangle-inequality envelope bounds all candidates simultaneously; a direct-score rule handles non-monotone candidate errors and, with an input-independent score, calibrates a static baseline under the same marginal guarantee. Under frozen-model and exchangeability assumptions, both rules bound the probability of issuing a prediction outside the budget and abstain when calibration is infeasible. On Burgers and Darcy flow across three training seeds, mode selection reduces active spectral support without a measurable latency reduction, because full-grid transforms and channel mixing dominate the cost. Narrowing channels does reduce Darcy forward cost, but reference-based selection must first compute the dense prediction. An input-only binary width selector avoids that pass and runs at 0.52-0.95 times dense latency; yet static widths calibrated under the same rule are often as fast or faster, and on a separately generated 1,000-example test set they generally achieve higher coverage, while the selector falls below its 90% target in more than half of the settings. Adaptive computation in neural operators should therefore be judged by achieved coverage and complete runtime against a matched static comparator.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Conformal Uncertainty Quantification Guarantees for Neural Operators

    Aug 28, 2026Tom Stent, Nicolas BoulléFair Conformal PredictionUncertainty Quantification

  2. A Bregman Proximal Viewpoint on Neural Operators

    Oct 14, 2026Abdel-Rahim Mezidi, Jordan Patracone, Saverio Salzo +4Neural OperatorsFourier Neural Operator

  3. Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver

    Sep 21, 2026Daniel Zhengyu Huang, Andrew M. StuartNeural Surrogate ModelingNeural PDE Solvers