Year: 2026
Type: preprint
Abstract: Differentiable optimization layers are traditionally integrated in predict-then-optimize frameworks where a neural model estimates parameters that subsequently serve as fixed inputs to downstream decision-making optimization problems. In this work, we introduce the concept of a "fairness layer": a differentiable optimization layer appended to a model's output layer that guarantees a chosen notion of output parity is satisfied when integrated into a neural network. Additionally, we introduce an online primal-dual inference algorithm that provides provable aggregate fairness guarantees for streaming predictions with arbitrarily small batch sizes, where traditional per-batch constraints become overly restrictive. Numerical experiments demonstrate the effectiveness of the fairness layer and associated algorithm, and theoretical analysis characterizes the layer's differentiability and stability properties during model training and backpropagation. Our code for these experiments is publicly available on GitHub (https://github.com/dtroxell19/FairDL-ICML-2026.git) and our public Python package documentation can be found online: https://dtroxell19.github.io/fairness_training/.
Source: arXiv (Cornell University)
Authors: Troxell, David, Roemer, Noah, Montúfar, Guido
Institution: University of California, Los Angeles
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G179296578, Kombinatorische und implizite Methoden für Deep Learning, G442688124, G4712284355, Collaborative Research: RI: Medium: MoDL: Occams Razor in Deep and Physical Learning, CAREER: Neural Networks in the Practical Regime, Collaborative Research: AIMing: Synergistic Advancement of AI and Mathematics
OpenAlex ID: W7161675569