We identify conditional parity as a general notion of non-discrimination in machine learning. In fact, several recently proposed notions of non-discrimination, including a few counterfactual notions, are instances of conditional parity. We show that conditional parity is amenable to statistical analysis by studying ran…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
17 results for “non-discrimination”
Study combines expert advice to avoid discrimination without violating equalized error rates.
problem Combining expert advice to avoid discrimination without violating equalized error rates.
method Running separate instances of the classical multiplicative weights algorithm for each group.
result Even for equalized error rates, algorithms with stronger performance guarantees than multiplicative weights cannot preserve non-discrimination.
Discrimination-aware classification is receiving an increasing attention in data science fields. The pre-process methods for constructing a discrimination-free classifier first remove discrimination from the training data, and then learn the classifier from the cleaned data. However, they lack a theoretical guarantee f…
Mitigates bias in text classification by weighting instances.
problem Unintended biases in text classification datasets based on demographic terms.
method Instance weighting to recover non-discrimination distribution.
result Effective mitigation of unintended biases without sacrificing generalization.
Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We propose a convex optimization for learning a data transformation with three goals: controlling discrimination, limiting distor…
As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpr…
Paper proposes fair decision trees to avoid unfair treatment.
problem Discriminative decision-making in automated systems.
method Mixed-integer optimization framework for fair decision trees.
result Improves fairness and accuracy in decision-making.
Most approaches in algorithmic fairness constrain machine learning methods so the resulting predictions satisfy one of several intuitive notions of fairness. While this may help private companies comply with non-discrimination laws or avoid negative publicity, we believe it is often too little, too late. By the time th…
Recent work on fairness in machine learning has focused on various statistical discrimination criteria and how they trade off. Most of these criteria are observational: They depend only on the joint distribution of predictor, protected attribute, features, and outcome. While convenient to work with, observational crite…
Paper protects privacy and fairness in deep learning models.
problem Ensuring fairness in deep learning models while protecting sensitive data.
method Uses differential privacy and Lagrangian duality to design fair predictors.
result Demonstrates improved model performance on prediction tasks.
DNLL loss improves deep LDA accuracy and consistency.
problem Pathological solutions in unconstrained Deep LDA.
method Introducing Discriminative Negative Log-Likelihood (DNLL) loss.
result Deep LDA trained with DNLL produces clean latent spaces and better calibrated probabilities.
Study reveals how features influence deep network decision boundaries.
problem Understanding the role of features in neural network decision boundaries.
method Adopted adversarial robustness tools to measure changes in CNN decision boundaries.
result Neural networks exhibit high invariance to non-discriminative features and are sensitive to small perturbations of training samples.
A method for learning fair representations for kernel models.
problem Ensuring fairness in machine learning models.
method Using Sufficient Dimension Reduction (SDR) in the context of kernel-based models to construct fair representations in the reproducing kernel Hilbert space (RKHS).
result Demonstrates the effectiveness of model-aware fair representations for kernel models, including support for multiple fairness criteria and continuous/discrete data.
Geotagged data can be used to describe regions in the world and discover local themes. However, not all data produced within a region is necessarily specifically descriptive of that area. To surface the content that is characteristic for a region, we present the geographical hierarchy model (GHM), a probabilistic model…
A new method for fairness in machine learning without explicit protected attributes.
problem Ensuring fairness in machine learning without explicit protected attributes.
method Example-based approach using paired consistency as a fairness regularizer.
result Demonstrated effectiveness on the Income Census dataset.
Study detects illegal discrimination by employers using correspondence experiments.
problem Detecting illegal discrimination by individual employers based on protected characteristics.
method Correspondence experiments, bounding higher moments of causal effects, decision rules for investigation.
result 85% of jobs contacting both white and black applicants are likely to discriminate.
Extends V-IP framework to use LLMs for generating task-relevant concepts, improving interpretability and performance.
problem Limited applicability of V-IP to small-scale tasks due to manual data annotation.
method Integrates Foundational Models with Large Language and Multimodal Models to generate and annotate concepts.
result FM+V-IP achieves better test performance with fewer concepts/queries compared to other frameworks.