The study tackles indirect discrimination in insurance pricing models.
problem Indirect discrimination in insurance pricing models.
method Presented a statistical model free of proxy discrimination.
result The canonical price in the model does not satisfy group fairness axioms.
Develops MGQDA for multi-group classification with theoretical guarantees and practical applications.
problem Complex multi-group classification problems with nonlinear decision boundaries and group-specific covariance patterns.
method MGQDA, a method based on quadratic discriminant analysis that projects predictors onto a lower-dimensional subspace.
result MGQDA achieves competitive or improved predictive performance compared to existing methods.
FairUDT uses uplift decision trees to detect and mitigate discrimination in training data.
problem Bias in machine learning classifiers due to historical discrimination or underrepresentation of minority groups.
method Integrates uplift modeling with decision trees and introduces a modified leaf relabeling approach for fairness.
result Achieves an acceptable accuracy-discrimination tradeoff while maintaining interpretability.
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.
FlipTest detects discrimination in classifiers using optimal transport.
problem Detecting discrimination in classifiers without causal information.
method Optimal transport to match individuals in different protected groups, creating similar pairs of in-distribution samples.
result FlipTest identifies subgroups that may be harmed by model discrimination, even when the model satisfies group fairness criteria.
Permutation of Weierstrass points on Veech surfaces in H(2) classified by discriminant.
problem Classifying permutations of Weierstrass points on Veech surfaces in H(2) based on discriminant. method Analyzing the permutation group induced by the affine group on Weierstrass points, considering both affine and Dehn multitwists.
result The permutation group is Dih4, Dih5, or Dih6 depending on the discriminant value. CST detects discrimination by comparing protected and non-protected individuals with a counterfactual.
problem Detecting discrimination in classifiers using legal fairness conditions.
method Operationalizes fairness given the difference using counterfactual reasoning.
result CST uncovers more discrimination cases than traditional situation testing.
This work provides statistical guarantees for GANs that are invariant to certain group symmetries.
problem Learning group-invariant distributions efficiently.
method Study of group-invariant GANs and their performance guarantees.
result Group-invariant GANs require fewer samples and have a reduced discriminator approximation error.
Structure-preserving GANs learn distributions with group symmetry efficiently.
problem Learning distributions with group symmetry efficiently.
method Developed structure-preserving GANs by reducing the discriminator space and designing structured generators.
result Significantly improved sample fidelity and diversity in small data regimes.
We prove that the discriminant of a nonsingular space curve of genus g≥2 is stable with respect to the standard action of the special linear group.
The study quantifies and compares aleatoric and epistemic discrimination in ML models.
problem Sources of discrimination in ML models and their impact on performance.
method Quantifying aleatoric and epistemic discrimination using statistical experiments and model accuracy.
result State-of-the-art fairness interventions are effective at removing epistemic discrimination but not aleatoric discrimination in datasets with missing values.
The paper calculates the Saito determinant for Coxeter discriminant strata.
problem Calculating the Saito determinant for specific geometric strata.
method Using the Saito flat metric and Lie derivatives, the paper finds the determinant of the metric restricted to Coxeter discriminant strata.
result The determinant of the Saito metric on Coxeter discriminant strata is proportional to a product of linear factors in flat coordinates.
We consider the discriminant locus of the Fermat cubic under the twistor fibration CP3⟶S4. We show that it has a conformal symmetry group of order 72 and use this to identify its topology.
The paper shows FtU can reduce discrimination without sacrificing accuracy.
problem Discrimination in machine learning predictions.
method Theoretical and empirical analysis of FtU, connecting with Model Multiplicity.
result FtU can reduce discrimination without reducing accuracy.
Deep learning models can discriminate against certain groups, requiring computational methods to ensure fairness.
problem Algorithmic discrimination in deep learning models affecting protected groups.
method Interpretability and mitigation approaches at different stages of deep learning lifecycle.
result Interpretability aids in diagnosing and mitigating algorithmic discrimination in deep learning.
Discriminative clustering uses mutual information to cluster data.
problem Clustering data into cohesive groups.
method Discriminative clustering using mutual information.
result Mutual information has been a cornerstone of discriminative clustering.
New method improves unsupervised feature learning for natural data.
problem Natural data's correlated and long-tail distribution challenges instance-level contrastive learning.
method Cross-level instance-group discrimination (CLD) to integrate between-instance similarity.
result CLD achieves new state-of-the-art performance on various datasets.
We address the problem of correcting group discriminations within a score function, while minimizing the individual error. Each group is described by a probability density function on the set of profiles. We first solve the problem analytically in the case of two populations, with a uniform bonus-malus on the zones whe…
A new algorithm balances fairness in clustering to avoid discrimination.
problem Clustering data can unfairly discriminate against different demographic groups.
method Designing a stochastic alternating balance fair k-means algorithm (SAfairKM) that alternates between k-means updates and group swap updates.
result The algorithm efficiently constructs well-spread and high-quality Pareto fronts on synthetic and real datasets.
A new DRM classifier for high-dimensional and imbalanced data.
problem Classification in high-dimensional and imbalanced data.
method Discriminative regression approach with iterative algorithms.
result Superior performance compared to state-of-the-art classifiers.
The paper studies 8D manifolds with a specific tensor field called a cubic discriminant.
problem Characterizing and understanding 8D Riemannian manifolds with reduced structure groups.
method Introducing an almost quaternion-Hermitian structure and a cubic discriminant tensor field.
result Only two non-flat, integrable examples of these structures are found: quaternion-Kähler symmetric spaces.
We present a novel approach to the formulation and the resolution of sparse Linear Discriminant Analysis (LDA). Our proposal, is based on penalized Optimal Scoring. It has an exact equivalence with penalized LDA, contrary to the multi-class approaches based on the regression of class indicator that have been proposed s…
This article considers the problem of multi-group classification in the setting where the number of variables p is larger than the number of observations n. Several methods have been proposed in the literature that address this problem, however their variable selection performance is either unknown or suboptimal to…
Develops DDC to improve clustering with deep neural networks.
problem Low-level indiscriminative representations and lack of pattern relationships in traditional clustering methods.
method Introduces global and local constraints to a deep neural network for adaptive relationship estimation and high-level representation learning.
result DDC outperforms current methods on multiple datasets.
This paper addresses dynamic price discrimination with fairness constraints.
problem Dynamic price discrimination with fairness constraints in online retailing.
method Nonparametric demand models, dynamic pricing policy, regret minimization.
result Optimal dynamic pricing policy with ildeO(T4/5) regret for price fairness. We define an integer-valued non-degenerate bi-invariant metric (the discriminant metric) on the universal cover of the identity component of the contactomorphism group of any contact manifold. This metric has a very simple geometric definition, based on the notion of discriminant points of contactomorphisms. Using gene…
For mass spectra acquired from cancer patients by MALDI or SELDI techniques, automated discrimination between cancer types or stages has often been implemented by machine learnings. These techniques typically generate "black-box" classifiers, which are difficult to interpret biologically. We develop new and efficient s…
New framework improves classification accuracy using Pillai's trace and ULDA.
problem Traditional LDA's limitations in noise sensitivity and non-invertible matrices.
method Integrates Pillai's trace with ULDA for a unified classifier.
result Effective control of Type I error rates and improved classification accuracy.
Predictive models learned from historical data are widely used to help companies and organizations make decisions. However, they may digitally unfairly treat unwanted groups, raising concerns about fairness and discrimination. In this paper, we study the fairness-aware ranking problem which aims to discover discriminat…
Linear and Quadratic Discriminant analysis (LDA/QDA) are common tools for classification problems. For these methods we assume observations are normally distributed within group. We estimate a mean and covariance matrix for each group and classify using Bayes theorem. With LDA, we estimate a single, pooled covariance m…
Logistic LDA applies LDA to non-categorical data.
problem Applying LDA to non-categorical data is challenging.
method Logistic LDA, a discriminative variant of LDA.
result Logistic LDA can learn from unlabeled data.
SDSM extracts statistically significant sub-trajectories from large trajectory datasets.
problem Discerning moving patterns that are more characteristic of one group of trajectories than another.
method Statistically Discriminative Sub-trajectory Mining (SDSM) method using tree representation and permutation-based statistical inference.
result SDSM efficiently extracts statistically significant sub-trajectories from massive trajectory datasets.
Paper discusses sliced generative models for improved sample discrimination.
problem Improving sample discrimination in generative models.
method One-dimensional slicing of AutoEncoder-based generative models, focusing on normality tests and classical distances.
result The second group of methods based on classical distances gives a faster decrease rate of Fréchet Inception Distance (FID).
This paper discusses fairness in machine learning and its legal implications.
problem Discrimination in machine learning algorithms that unfairly treat certain groups.
method Explains moral philosophy, legislation, and strategies to detect and prevent discrimination.
result Discusses the need for fairness in machine learning and legal measures to enforce it.
Clustering in high-dimensional spaces is nowadays a recurrent problem in many scientific domains but remains a difficult task from both the clustering accuracy and the result understanding points of view. This paper presents a discriminative latent mixture (DLM) model which fits the data in a latent orthonormal discrim…
This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose cross-label suppression constraint to enlarge the difference among representations for differe…
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.
Recent studies in the literature have paid much attention to the sparsity in linear classification tasks. One motivation of imposing sparsity assumption on the linear discriminant direction is to rule out the noninformative features, making hardly contribution to the classification problem. Most of those work were focu…
We show that for every nonelementary representation of a surface group into SL(2,C) there is a Riemann surface structure such that the Higgs bundle associated to the representation lies outside the discriminant locus of the Hitchin fibration.
Paper presents mdfa to identify victims of discrimination in black box classifiers.
problem Identifying victims of discrimination in black box classifiers.
method Reduces discrimination measurement to matching distributions and sensitive attribute coincidence prediction.
result Identifies African-American individuals at high risk of violent recidivism.
New algorithm reduces discrimination in predictions.
problem Tackles potential discrimination in AI predictions.
method Integrates fairness adjustments into tree-building process.
result Reduces discriminatory predictions without significant loss in accuracy.
Classifies extended Abelian Chern-Simons theories using quadratic modules.
problem Classifying extended Abelian Chern-Simons theories.
method Using quadratic modules to classify theories.
result Finite quadratic modules classify extended Abelian Chern-Simons theories.
The paper proposes a method to select clusters, models, and algorithms based on quadratic discriminant scores.
problem Selecting the number of clusters, models, and algorithms in cluster analysis.
method Develops quadratic scores for cluster quality, uses bootstrap resampling, and compares partitions.
result The proposed method achieves better overall performance compared to other state-of-the-art methods.
We consider the problem of high-dimensional classification between the two groups with unequal covariance matrices. Rather than estimating the full quadratic discriminant rule, we propose to perform simultaneous variable selection and linear dimension reduction on original data, with the subsequent application of quadr…
GRAD simplifies making neural networks fair.
problem No methods for making neural networks fair.
method Gradient Reversal Against Discrimination (GRAD)
result Improved individual and group fairness.
FAE framework tackles fairness in machine learning by balancing data and adjusting decision boundaries.
problem Discrimination in automated decision-making based on machine learning algorithms.
method Combines pre- and post-processing fairness interventions to address group imbalance, class imbalance, and class overlap.
result Improves fairness in machine learning models by balancing data and adjusting decision boundaries.
Lattices embeddability determined by correction terms.
problem Embeddability of nonunimodular definite lattices.
method Using Elkies' theorem and lattice correction terms.
result Embeddability of lattices is determined by correction terms.
Study groups formed by words in braid monoid.
problem Invariance properties of braid group presentations.
method Generalized presentations of braid groups and studied their invariance under operations.
result Groups depend only on conjugacy class in braid group under mild hypotheses.