Data-driven algorithms play a large role in decision making across a variety of industries. Increasingly, these algorithms are being used to make decisions that have significant ramifications for people's social and economic well-being, e.g. in sentencing, loan approval, and policing. Amid the proliferation of such sys…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “bias metrics”
This report examines the Pinned AUC metric introduced and highlights some of its limitations. Pinned AUC provides a threshold-agnostic measure of unintended bias in a classification model, inspired by the ROC-AUC metric. However, as we highlight in this report, there are ways that the metric can obscure different kinds…
Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of threshold-agnostic metrics that provide a nuanced view of this unintended bias, by…
Study improves confidence measures in medical imaging pipelines by addressing bias.
problem Bias in metric-based imaging pipelines compromises the efficiency of prediction intervals.
method Formalized symmetric and asymmetric CP formulations, analyzed bias effects, and validated empirically.
result Symmetric intervals are inflated by bias, while asymmetric intervals remain unaffected.
Study uncovers bias in image classification models using attribution maps.
problem Data bias in image classification models.
method Created an artificial dataset with known bias, trained CNNs, and used attribution maps to inspect decisions.
result Different attribution map techniques highlight bias better than others, and metrics support bias identification.
This paper tackles bias in federated learning without compromising data privacy.
problem Bias in federated learning models.
method Three pre-processing and in-processing methods to mitigate bias.
result Proposed methods are effective even with skewed data distributions or a small number of participating parties.
This paper examines AI and ML bias and fairness issues.
problem Bias and unfairness in AI and ML algorithms.
method Overview of bias and fairness issues, types and sources of data bias, algorithmic unfairness, fairness metrics, and de-biasing techniques.
result Discussion of the limitations of fairness metrics and de-biasing techniques.
Paper introduces new importance metrics for machine learning models, linking them to CATE.
problem Interpreting black-box models' importance metrics due to data dependence and non-parametric nature.
method Introduces MVIM and CVIM, proposing permutation-based estimation and bias-variance decomposition.
result MVIM and CVIM have a quadratic relationship with CATE, addressing bias in correlated predictors.
This paper analyzes implicit bias in Deep Linear Discriminant Analysis.
problem The implicit bias of Deep Linear Discriminant Analysis.
method Analyzing gradient flow on a L-layer diagonal linear network.
result Under balanced initialization, the network transforms additive updates into multiplicative updates, conserving the (2/L) quasi-norm.
We model and correct bias in sequential evaluation, improving ranking accuracy.
problem Sequential evaluation bias in online, irrevocable scoring.
method Modeling the rating process, posing as statistical inference, proposing an online algorithm.
result Near-linear time, online algorithm with guarantees in ranking metrics, information theoretically optimal.
A new metric MSD detects bias in datasets efficiently.
problem Detecting bias in AI systems and datasets.
method Introduced Maximum Subgroup Discrepancy (MSD) metric and a practical algorithm based on MIO.
result MSD provides a linear sample complexity for practical applications, distinguishing biases effectively.
Mirror Langevin Algorithm converges with zero bias.
problem Achieving convergence with zero bias in discrete-time sampling.
method Discretization of Mirror Langevin Diffusion and mean-square analysis.
result Mirror Langevin Algorithm converges with zero bias.
Ranking metrics are a family of metrics largely used to evaluate recommender systems. However they typically suffer from the fact the reward is affected by the order in which recommended items are displayed to the user. A classical way to overcome this position bias is to uniformly shuffle a proportion of the recommend…
New neural nets respect triangle inequality, improving graph and reinforcement learning performance.
problem Neural nets lack inductive bias for certain subadditive distances.
method Introduced novel architectures that universally approximate norm-induced metrics.
result Neural nets with triangle inequality inductive bias outperform existing approaches.
Paper proposes synthetic data generator to study and mitigate bias in machine learning.
problem Bias in machine learning data can lead to unfair outcomes.
method Developed a synthetic data generator to introduce and analyze various types of bias.
result Demonstrated how synthetic data can be used to study and mitigate bias in machine learning models.
Paper presents a new algorithm to approximate Wasserstein-2 barycenters without bias.
problem Approximating Wasserstein-2 barycenters of continuous measures.
method Generative model approach using arbitrary neural networks.
result The method does not introduce bias and is applicable to large-scale tasks.
This paper evaluates fairness in deep metric learning and proposes a method to reduce subgroup performance gaps.
problem The negative impact of deep metric learning representations on minority subgroup performance in downstream tasks.
method Definition of fairness in DML through inter-class, intra-class, and uniformity properties; finDML benchmark; Partial Attribute De-correlation (PARADE) method.
result Bias in DML representations propagates to downstream tasks, even with balanced training data.
UBM transfers bias mitigation from upstream to downstream tasks efficiently.
problem Bias in fine-tuned language models across various tasks.
method Apply bias mitigation to an upstream model, then fine-tune a downstream model on this mitigated model.
result UBM effects transfer to new downstream tasks, creating less biased models.
Is Your Model "MADD"? A Novel Metric to Evaluate Algorithmic Fairness for Predictive Student Modelscs.LG
New metric MADD assesses fairness of predictive student models.
problem Predictive student models can be biased and unfair, leading to discrimination.
method Proposes MADD metric to analyze model's discriminatory behaviors.
result Fair predictive performance does not guarantee fair behaviors or outcomes.
SkewSize detects model biases by analyzing mistakes across subgroups.
problem Benchmarking model performance in the presence of spurious correlations.
method Introducing SkewSize, a metric that captures bias from model mistakes.
result SkewSize highlights biases not captured by other metrics.
This research debiases machine unlearning by using counterfactual examples.
problem Machine unlearning processes can be biased, leading to inaccurate results.
method Intervention-based approach using counterfactual examples to mitigate biases.
result The method outperforms existing baselines on evaluation metrics.
New method reduces gender bias in language models without harming performance.
problem Bias in language models learned from biased data.
method Causal analysis to identify problematic model components, followed by linear projection of weight matrices.
result DAMA significantly decreases bias in language models while maintaining performance.
NNLMs optimize poorly for word probabilities due to embedding space structure.
problem NNLMs assign suboptimal probabilities to some words.
method Analyzed the inductive bias of NNLMs and the structure of word embeddings.
result Words on the convex hull have bounded probability, affecting others.
Study shows fairness metrics are unreliable for small datasets in NLP tasks.
problem Unreliable fairness metrics for small datasets in NLP tasks.
method Experiments on Bios dataset with varying model sizes.
result Common fairness indices provide unreliable results for small samples.
New method quantifies inductive bias for machine learning tasks.
problem Quantifying the amount of inductive bias in machine learning models.
method Estimates inductive bias by modeling loss distribution of random hypotheses.
result Higher dimensional tasks require greater inductive bias.
A2A metric evaluates bias correction methods, reducing ATE estimation errors.
problem Selection biases in non-randomized studies of medical treatments.
method Propensity score matching (PSM) with novel metric A2A.
result Reduces ATE estimation errors by up to 90% across synthetic and real-world datasets.
JKO scheme adds deceleration in rapidly changing metric curvature directions.
problem Understanding the implicit bias of the JKO scheme in Wasserstein gradient flow.
method Characterized the implicit bias of the JKO scheme at second order in η, modifying the energy functional.
result JKO scheme adds deceleration in directions where metric curvature of J is rapidly changing.
This paper examines fairness and arbitrariness in bias mitigation methods.
problem Understanding how different bias mitigation strategies affect individual predictions and whether they introduce arbitrariness.
method FRAME framework to evaluate bias mitigation through five dimensions: Impact Size, Change Direction, Decision Rates, Affected Subpopulations, and Neglected Subpopulations.
result Significant differences in the behaviors of debiasing methods were exhibited, highlighting the limitations of current fairness criteria and the inherent arbitrariness in the debiasing process.
Study improves statistical power for detecting algorithmic bias in educational data.
problem Challenges in measuring algorithmic bias using ABROCA due to skewed distribution.
method Investigates ABROCA's distributional properties and proposes nonparametric randomization tests.
result ABROCA-based bias assessments are underpowered in typical EDM sample sizes.
A learned generative model often produces biased statistics relative to the underlying data distribution. A standard technique to correct this bias is importance sampling, where samples from the model are weighted by the likelihood ratio under model and true distributions. When the likelihood ratio is unknown, it can b…
In unsupervised data generation tasks, besides the generation of a sample based on previous observations, one would often like to give hints to the model in order to bias the generation towards desirable metrics. We propose a method that combines Generative Adversarial Networks (GANs) and reinforcement learning (RL) in…
In critical decision-making scenarios, optimizing accuracy can lead to a biased classifier, hence past work recommends enforcing group-based fairness metrics in addition to maximizing accuracy. However, doing so exposes the classifier to another kind of bias called infra-marginality. This refers to individual-level bia…
fairmodels tool detects and mitigates bias in machine learning models.
problem Bias in machine learning models leading to discrimination.
method Model-agnostic approach to bias detection, visualization, and mitigation.
result Validates fairness and eliminates bias in classification models.
ABROCA assesses algorithmic bias, revealing skewed distributions that inflate results.
problem Detecting nuanced performance differences in classifier fairness.
method Study of ABROCA metric's statistical properties under various conditions.
result ABROCA distributions are skewed, inflating results by chance in imbalanced classes.
Exposure bias has been regarded as a central problem for auto-regressive language models (LM). It claims that teacher forcing would cause the test-time generation to be incrementally distorted due to the training-generation discrepancy. Although a lot of algorithms have been proposed to avoid teacher forcing and theref…
Improved sampling efficiency with Random Reshuffling for Langevin dynamics.
problem Sampling efficiency in stochastic gradient algorithms.
method Random Reshuffling for Stochastic Gradient Langevin Dynamics (SGLD).
result Random Reshuffling leads to improved performance in sampling.
New clustering method considers causal fairness to avoid bias.
problem Clustering algorithms can unintentionally propagate unfair disparities.
method Integrates causal fairness metrics into clustering algorithms.
result Demonstrates efficacy on datasets with known unfair biases.
Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairnessstat.ML
New framework for interpreting disaggregated fairness evaluations using causal models.
problem Misinterpretation of disaggregated fairness evaluations due to data representativeness and selection bias.
method Causal graphical models to characterize fairness properties and metric stability under different data generating processes.
result Disaggregated evaluations are unreliable without explicit assumptions regarding bias mechanisms.
Study evaluates bias mitigation methods in deep learning, finds they often exploit hidden biases.
problem Deep learning systems learn biases, affecting performance on minority groups.
method Improved evaluation protocol, new dataset, robustness across different tuning distributions.
result Bias mitigation methods often exploit hidden biases, are not robust to multiple forms of bias, and are sensitive to tuning set choice.
The paper assesses fairness in AI for financial services, using statistical methods.
problem Unintentional bias and insufficient model validation in AI applications.
method Statistical methods for imbalanced data treatment and bias mitigation.
result Fairness evaluation metrics applied to a credit card default payment example.
Exactly solvable model reveals how data geometry influences ML bias.
problem How data geometry affects machine learning bias.
method High-dimensional data imbalance model, statistical physics tools.
result Exact predictions for fairness metrics and mitigation strategies.
The unadjusted Langevin algorithm converges faster for some variables in high dimensions.
problem Sampling probability distributions in high-dimensional settings.
method Analysis of the unadjusted Langevin algorithm for strongly log-concave distributions.
result The delocalization of bias effect allows for faster convergence for a small number of variables.
The paper addresses insurance pricing by improving machine learning models and metrics.
problem Lack of balance and confusion in insurance model performance metrics.
method Introduces autocalibration and Tweedie deviance minimization for insurance pricing models.
result Autocalibration corrects bias and ensures balance on local scales.
Propensity score matching improves fairness in machine learning models.
problem Bias in training data affects fairness metrics in machine learning models.
method Propensity score matching to evaluate and mitigate bias in test data.
result FairMatch significantly reduces bias in test data without sacrificing predictive performance.
In the past decades, intensive efforts have been put to design various loss functions and metric forms for metric learning problem. These improvements have shown promising results when the test data is similar to the training data. However, the trained models often fail to produce reliable distances on the ambiguous te…
In this paper, we provide a theoretical understanding of word embedding and its dimensionality. Motivated by the unitary-invariance of word embedding, we propose the Pairwise Inner Product (PIP) loss, a novel metric on the dissimilarity between word embeddings. Using techniques from matrix perturbation theory, we revea…
In this paper we introduce a new inductive bias for capsule networks and call networks that use this prior -capsule networks. Our inductive bias that is inspired by TE neurons of the inferior temporal cortex increases the adversarial robustness and the explainability of capsule networks. A theoretical framework with…
Machine fairness is impossible to achieve fully due to historical biases.
problem Machine learning models inherit biases from historical data, making it impossible to satisfy fairness metrics simultaneously.
method Presented a causal perspective to the impossibility theorem of fairness.
result It is impossible to satisfy fairness metrics like demographic parity, equal opportunity, and equalized odds simultaneously.