# Safe Domain Adaptation for Physics: Overcoming Nuisances, Label Shifts, and Simulation Priors

arXiv: https://arxiv.org/abs/2608.18190 · HTML: https://mlsanity.com/paper/2608.18190/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks](https://mlsanity.com/paper/2009.11848/) (2020)
- [Sensitivity and Generalization in Neural Networks: an Empirical Study](https://mlsanity.com/paper/1802.08760/) (2018)
- [Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping](https://mlsanity.com/paper/1709.07857/) (2017)
- [Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift](https://mlsanity.com/paper/2003.04475/) (2020)
- [An introduction to domain adaptation and transfer learning](https://mlsanity.com/paper/1812.11806/) (2018)
- [Importance Weighted Adversarial Nets for Partial Domain Adaptation](https://mlsanity.com/paper/1803.09210/) (2018)
- [Domain-Adversarial Neural Networks](https://mlsanity.com/paper/1412.4446/) (2014)
- [Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation](https://mlsanity.com/paper/2103.12857/) (2021)
- [Feature contamination: Neural networks learn uncorrelated features and fail to generalize](https://mlsanity.com/paper/2406.03345/) (2024)
- [Domain-Adaptive Neural Posterior Estimation for Strong Gravitational Lens Analysis](https://mlsanity.com/paper/2410.16347/) (2024)
- [Improving Robustness of Jet Tagging Algorithms with Adversarial Training](https://mlsanity.com/paper/2203.13890/) (2022)
- [Sim-to-Real Domain Adaptation For High Energy Physics](https://mlsanity.com/paper/1912.08001/) (2019)
- [Deep learning method for identifying mass composition of ultra-high-energy cosmic rays](https://mlsanity.com/paper/2112.02072/) (2021)

## Abstract (arXiv)

Domain adaptation is widely used to make neural networks trained on simulations applicable to experimental data. Its premise is that the two domains differ only in nuisances, and that the quantity of interest is distributed identically in both. In physics neither assumption holds: simulations can be wrong about the physics, and the distribution of the target quantity - an energy spectrum, a redshift distribution - is often the measurement itself. We study the consequences of such mismatches on a toy air-shower benchmark in which a detector-response nuisance, a physical simulation shift, and an energy-spectrum shift can be switched on separately or together. Standard adversarial adaptation handles the conditional shifts, but once the two spectra differ it aligns them, replacing an uncontrolled bias by one anchored on the simulation prior. We present adaptive domain adaptation, which reweights the simulated events so as to focus domain adaptation on the genuine physical mismatch alone. Since the predicted spectrum depends on model training configuration, we provide a label-free model selection rule for selecting the near-the-best operation point.