Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Troxell, David, Roemer, Noah, Montúfar, Guido
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913136012951552
author Troxell, David
Roemer, Noah
Montúfar, Guido
author_facet Troxell, David
Roemer, Noah
Montúfar, Guido
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17118
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
Troxell, David
Roemer, Noah
Montúfar, Guido
Machine Learning
Computation
Primary 68T07, Secondary 90C25, 90C30, 62R07
I.2.6; G.1.6; K.4.1
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/.
title Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
topic Machine Learning
Computation
Primary 68T07, Secondary 90C25, 90C30, 62R07
I.2.6; G.1.6; K.4.1
url https://arxiv.org/abs/2605.17118