The bias potential model explains how generative models can generalize or memorize samples.
problem Understanding and achieving generalization in generative models like GANs.
method Introducing the bias potential model to analyze the behavior of generative models.
result Dimension-independent generalization accuracy can be achieved with early stopping in the bias potential model.
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…
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…
Mirror flow in shallow neural networks shows similar implicit bias to gradient flow, with key differences in curvature penalties.
problem Analyzing implicit bias in shallow neural networks with mirror flow.
method Characterization through variational problems and scaled potentials.
result Mirror flow with scaled potentials induces a rich class of biases not captured by RKHS norms.
The paper introduces Relative Bias to quantify LLM bias systematically.
problem Quantifying bias in LLMs is challenging due to ambiguity and rapid model emergence.
method Relative Bias framework using Embedding Transformation and LLM-as-a-Judge methodologies.
result The two scoring methods show strong alignment, providing a systematic approach.
Machine learning can improve 2SLS first stage predictions, but nonlinear methods often introduce bias.
problem Improving the first stage of 2SLS using machine learning.
method Decomposed bias into three components, investigated through simulation.
result Nonlinear machine learning methods can introduce substantial bias in second-stage estimates.
Gradient clipping helps private SGD converge despite potential bias.
problem Gradient clipping in private SGD can bias convergence.
method Theoretical analysis and empirical evaluation of gradient clipping effects.
result Gradient clipping can prevent convergence to stationary points and introduces bias.
Over the past two decades, the notion of implicit bias has come to serve as an important component in our understanding of discrimination in activities such as hiring, promotion, and school admissions. Research on implicit bias posits that when people evaluate others -- for example, in a hiring context -- their unconsc…
Reduces gender bias in patient notes while maintaining medical classification accuracy.
problem Bias in natural language processing of patient notes.
method Identifying and removing gendered language using BERT-based classifiers, then augmenting data to maintain performance.
result Minimal degradation in health condition classification tasks with data augmentation.
In classification problems, sampling bias between training data and testing data is critical to the ranking performance of classification scores. Such bias can be both unintentionally introduced by data collection and intentionally introduced by the algorithm, such as under-sampling or weighting techniques applied to i…
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.
We study the implicit bias of generic optimization methods, such as mirror descent, natural gradient descent, and steepest descent with respect to different potentials and norms, when optimizing underdetermined linear regression or separable linear classification problems. We explore the question of whether the specifi…
We discovered secular trend bias in a drug effectiveness study for a recently approved drug. We compared treatment outcomes between patients who received the newly approved drug and patients exposed to the standard treatment. All patients diagnosed after the new drug's approval date were considered. We built a machine …
Updating predictive models introduces bias, leading to miscalibration.
problem Bias introduced when updating predictive models after interventions.
method Proposed a causal framework and partially observed Markov decision process.
result Successive predictive scores may converge to undesirable outcomes.
Theory and methods to mitigate omitted variable bias in causal machine learning.
problem Mitigating omitted variable bias in causal machine learning models.
method Developed a general theory and flexible statistical inference methods for bounding and testing the magnitude of omitted variable bias.
result Simple plausibility judgments can bound the magnitude of omitted variable bias in complex, nonlinear models.
Method fuses low and high-resolution data for better health estimates.
problem Improving high-resolution health estimates from mixed data sources.
method Fusion of unbiased low-resolution and potentially biased high-resolution data, learning a distribution consistent with sampling bias.
result Significant reduction in bias in high-resolution estimates.
Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be addressed, particularly the potential for unintentional discrimination. We present an…
Paper detects bias in AI medical models using CART.
problem Ensuring fairness in AI medical decision support systems.
method Uses Classification and Regression Trees (CART) algorithm to identify bias.
result Validated the CART approach in both synthetic and real-world data.
Improved 3D generative models for drug design reduce bias and enhance data efficiency.
problem Data sparsity and bias in 3D molecular design models.
method Multi-level contrastive learning protocol for bias control and data efficiency.
result Hierarchical generative models that are topologically unbiased and explainable.
New method preserves GCM spatial dependencies for better climate projections.
problem Systemic biases in GCM output and loss of spatial/temporal dependencies.
method SPECD approach using Vecchia approximation and semi-parametric quantile regression.
result SPECD preserves key marginal and joint distribution properties of precipitation and temperature.
This paper tackles selection bias in recommender systems by considering the neighborhood effect.
problem Selection bias in recommender systems due to filtering and user selection.
method Formalizes neighborhood effect as interference problem, introduces treatment representation, and proposes ideal loss.
result Proposed methods achieve unbiased learning when both selection bias and neighborhood effect are present.
A new algorithm for fair decision-making in bandit problems with biased feedback.
problem Fair allocation of resources across sensitive groups in bandit problems with biased feedback.
method Proposes a novel algorithm that learns a societal bias term to mitigate unfairness in multi-armed bandit problems.
result The proposed algorithm achieves a theoretical bound on regret and demonstrates fairness in synthetic and real-world data.
We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. We analyze the potential allocation harms that can result from semantic representation bias. To do so, we study the impact on occupation classification of…
SGD benefits from a directional bias in kernel regression models.
problem Improving generalization in kernel regression models.
method Generalized directional bias property of SGD in kernel regression.
result SGD converges along the eigenvector of the largest eigenvalue of the Gram matrix.
Distillation affects some classes more than others, impacting fairness and bias.
problem Distillation affects some classes more than others, impacting fairness and bias.
method Examined class-wise accuracy and fairness metrics (DPD, EOD) on models trained with different datasets.
result Increasing the distillation temperature improves the distilled student model's fairness and individual fairness.
Paper addresses selection bias in online advertising auctions.
problem Selection bias affects auction truthfulness and advertiser profits.
method Theoretical analysis combined with multi-task learning.
result Selection bias can be significantly reduced using multi-task learning.
Paper models market dynamics using bull and bear forces.
problem Complex market dynamics influenced by biases and narratives.
method Bias to Behavior from Bull-Bear Dynamics (B4) model.
result Model predicts market trends with superior performance and interpretable insights.
New scoring rule predicts causal relations from data with selection bias.
problem Discovering causal relations from independence constraints under selection bias and confounding.
method Local Y-Structure patterns and a scoring rule for Y-Structures.
result Y-Structure scoring rule successfully predicts causal relations in real-world data.
Efficiently scales continuous kernels with sparse Fourier domain learning.
problem High computational and memory demands, spectral bias in continuous kernels.
method Sparse learning in the Fourier domain.
result Efficient scaling of continuous kernels, reduced computational and memory requirements, mitigated spectral bias.
New method corrects selection bias in complex models.
problem Selection bias in statistical studies leading to systematic distortions.
method Amortized Bayesian inference with neural posterior estimation.
result Recover well-calibrated posterior distributions across diverse selection mechanisms.
The paper tackles sampling bias in credit scoring models and proposes methods to improve their training and evaluation.
problem Sampling bias in credit scoring models leads to an incomplete representation of the borrower population.
method Bias-aware self-learning framework and Bayesian evaluation method to correct for bias.
result Bayesian evaluation outperforms standard accuracy measures in predicting future performance.
New method uses biased MD to create accurate MLIPs.
problem Creating a comprehensive data set for MLIPs.
method Bias MD by MLIP's energy uncertainty, using gradient-based uncertainties.
result Develops uniformly accurate MLIPs with lower computational cost.
Model improves CVR estimation in recommender systems by mitigating bias and overlooking causal relationships.
problem Data sparsity and sample selection bias in CVR estimation.
method Entire Space Counterfactual Multitask Model (ESCM2) incorporating counterfactual risk minimizer. result Significantly enhances recommendation performance by effectively mitigating bias and overlooking causal relationships.
Study evaluates if LLMs have company-specific biases in financial sentiment analysis.
problem Evaluating if large language models exhibit company-specific biases in financial sentiment analysis.
method Comparing sentiment scores with and without company names, constructing economic models, and empirical analysis.
result LLMs show company-specific biases in sentiment analysis, impacting investor behavior and stock prices.
Cross-validation is the de facto standard for predictive model evaluation and selection. In proper use, it provides an unbiased estimate of a model's predictive performance. However, data sets often undergo various forms of data-dependent preprocessing, such as mean-centering, rescaling, dimensionality reduction, and o…
The paper analyzes optimal implicit bias in linear regression for over-parameterized models.
problem Finding the best generalization performance in over-parameterized linear regression.
method Asymptotic analysis of generalization performance for convex functions/potentials.
result Optimal implicit bias that achieves the best generalization error under certain conditions.
Large batch training with DP-SGD reduces model performance due to implicit bias.
problem Large batch training with DP-SGD reduces model performance.
method The study analyzes the phenomenon of implicit bias in Noisy-SGD (DP-SGD without clipping) and its theoretical solutions for linear models.
result The implicit bias in large batch training with DP-SGD is amplified by additional noise, similar to SGD.
Two-layer networks favor simple features, especially in complex datasets.
problem Simplicity bias in neural networks over-reliing on simple features.
method Characterization of two-layer neural networks with small weights and gradient flow.
result Features learned in middle training stages are more useful for out-of-distribution transfer.
A hybrid strategy forecasts short-term loads using Warm-start Gradient Tree Boosting.
problem Lack of effective short-term load forecasting methods.
method Hybrid strategy integrating four different inference models: tree-based ensemble method Warm-start Gradient Tree Boosting (WGTB).
result Demonstrates effectiveness of hybrid strategy on real datasets.
Meta-learning reduces training overhead for communication systems.
problem Inefficiency in machine learning due to frequent retraining when system configuration changes.
method Meta-learning selects a suitable inductive bias from related tasks, reducing training data and time requirements.
result Meta-learning can reduce training overhead for communication systems.
Paper tackles causal inference with partially labeled data, introducing robust methods.
problem Challenges in causal inference due to partially labeled datasets and potential bias.
method Decaying missing-at-random framework and BRSS estimator for doubly robust causal inference.
result Established asymptotic normality of BRSS estimator under decaying labeling propensity scores.
ADIGen: Automatic, Debiased, and Invariant Counterfactual Generation
problem Generative models for counterfactual outcomes
method ADIGen combines Riesz regression, causal invariance, and orthogonal statistical learning
result ADIGen controls counterfactual risk under general interventions
Study explores bias-variance in adversarial machine learning.
problem Understanding adversarial machine learning's impact on bias and variance.
method Investigates bias-variance trade-offs in deep neural networks using MSE and cross-entropy.
result Derives bias-variance trade-offs for classification and regression.
Study reveals how neural network biases align with adversarial attack frequencies.
problem Correlation between neural network biases and adversarial attacks.
method Fourier transform analysis of network implicit bias and adversarial perturbations.
result Network bias and adversarial attack frequencies are highly correlated.
Gradient flow in ReLU networks biases towards generalization but makes them vulnerable to adversarial attacks.
problem Generalization vs. Adversarial Robustness in ReLU Networks
method Analysis of gradient flow in two-layer ReLU networks with clustered data.
result Gradient flow biases towards generalization but also makes networks vulnerable to adversarial attacks.
This paper investigates bias in resampled backtests for financial portfolios, finding it often negligible.
problem Bias in resampled backtests for financial portfolio evaluation.
method Investigation of bias in rolling-window mean-variance portfolios using resampling techniques.
result The bias in Sharpe Ratio estimates from IID resampling is often a fraction of estimation noise, making it tolerable.
New RL algorithms correct bias in dynamic data analysis.
problem Dynamic data generation and analysis create endogeneity issues.
method Instrument variable (IV)-based reinforcement learning (RL) algorithms.
result Established theoretical properties of IV-RL algorithms.
Anonymizing company names in financial news improves trading performance, contrary to initial expectations.
problem Look-ahead and distraction biases in sentiment analysis of financial news.
method Investigated trading strategies based on original and anonymized headlines, comparing performance.
result Anonymized headlines outperform original in-sample, suggesting distraction effect is stronger.