# Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications

arXiv: https://arxiv.org/abs/2603.16377 · HTML: https://mlsanity.com/paper/2603.16377/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 10 of 10)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Invariance, Causality and Robustness](https://mlsanity.com/paper/1812.08233/) (2018)
- [Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach](https://mlsanity.com/paper/1904.05514/) (2019)
- [On the definition of a confounder](https://mlsanity.com/paper/1304.0564/) (2013)
- [Wasserstein distributional robustness of neural networks](https://mlsanity.com/paper/2306.09844/) (2023)
- [Binary Stochastic Filtering: feature selection and beyond](https://mlsanity.com/paper/2007.03920/) (2020)

## Abstract (arXiv)

Chronological age predictors often fail to achieve out-of-distribution (OOD) gen- eralization due to exogenous attributes such as race, gender, or tissue. Learning an invariant representation with respect to those attributes is therefore essential to improve OOD generalization and prevent overly optimistic results. In predic- tive settings, these attributes motivate bias mitigation; in causal analyses, they appear as confounders; and when protected, their suppression leads to fairness. We coherently explore these concepts with theoretical rigor and discuss the scope of an interpretable neural network model based on adversarial representation learning. Using publicly available mouse transcriptomic datasets, we illustrate the behavior of this model relative to conventional machine learning models. We observe that the outcome of this model is consistent with the predictive results of a published study demonstrating the effects of Elamipretide on mouse skeletal and cardiac muscle. We conclude by discussing the limitations of deriving causal interpretation from such purely predictive models.