Analyzes how bias evolves in SGD training across different data sub-populations.
problem Understanding bias formation during machine learning training.
method Analytical description of SGD dynamics in a teacher-student setup with Gaussian-mixture model.
result Different sub-populations influence bias at different timescales, revealing shifting classifier preferences.
Bayesian networks learn sub-population differences from data.
problem Inference from a single network structure can be misleading when data populations are heterogeneous.
method A mixture of Bayesian networks where component probabilities depend on individual characteristics.
result Identifies both network structures and demographic predictors of sub-population membership.
The paper proposes a new method for comparing logistic regression models across different populations.
problem Comparing logistic regression models across sub-populations can lead to misleading results.
method Develops a cascading set of equivalence tests for logistic regression models, addressing coding, predictions, and overall accuracy.
result Equivalence testing incentivizes accurate inference and avoids perverse incentives from significance tests.
Paper tackles causal effect identification in sub-population with latent variables.
problem Identify causal effects in a sub-population with latent variables.
method Extend relevant graphical definitions and propose an algorithm for the s-ID problem.
result Sound algorithm for s-ID problem with latent variables.
Estimates KL divergence with fairness considerations for sub-populations.
problem Fairly estimate KL divergence between distributions considering sub-populations.
method Proposes multi-group attribution for KL divergence estimation, derived from multi-calibration.
result Shows multi-group attribution provides better KL divergence estimates conditioned on sub-populations.
Develops a fair classifier for deep learning models.
problem Ensuring fairness in classification models across different sub-populations.
method Applies Rawlsian principles to minimize error rate on the worst-off sub-population.
result Introduces a practical method to adapt any black-box deep learning model to be fair.
Semi-supervised learning benefits the rich more than the poor, affecting fairness.
problem Disparate impact of semi-supervised learning on different sub-populations.
method Theoretical and empirical analysis of a broad family of SSL algorithms using pseudo-labels.
result Semi-supervised learning benefits the rich more than the poor, potentially violating fairness.
A new method identifies sub-populations in unlabelled heterogeneous data by accounting for co-features.
problem Estimating sub-populations in unlabelled heterogeneous data with co-features.
method Mixture of Conditional Gaussian Graphical Models (CGGM) with penalized EM algorithm.
result The method successfully identifies sub-populations disrupted by co-features.
Optimizes weights for better model performance in shifting data.
problem Improper importance weighting leads to poor model performance in data shifts.
method Interprets weights as a bias-variance trade-off and optimizes them simultaneously with model parameters.
result Optimizing weights significantly improves model generalization performance.
New privacy-preserving learning model for mixtures of private and public data.
problem Learning from datasets with both private and public data, where privacy concerns differ.
method Designing a differential privacy-preserving learning algorithm for a mixture of private and public sub-populations.
result Linear classifiers can be learned with sample complexity comparable to non-private PAC-learning, even when privacy status correlates with labels.
Develops robust learning methods for datasets with sub-populations.
problem Robust performance and generalization to unseen testing populations in datasets with sub-populations.
method Min-max-regret (MMR) formulation for distribution-free robust hierarchical model.
result Empirical MMR enjoys regret guarantees on training and unseen testing populations.
Unified framework for fairness, robustness, and distribution shifts.
problem Diverse failure modes of machine learning systems.
method Formalizes biases as violations of conditional independence and proves equivalence conditions.
result Equivalent effects of biases in different failure modes under specific conditions.
Proposes a stability evaluation criterion for learning models using distributional perturbations.
problem Ensuring reliable deployment of learning models in out-of-sample environments.
method Uses optimal transport discrepancy with moment constraints to quantify minimal perturbation required for model deterioration.
result Validates the practical utility of the stability evaluation criterion across various real-world applications.
We develop a behavioral asset pricing model in which agents trade in a market with information friction. Profit-maximizing agents switch between trading strategies in response to dynamic market conditions. Due to noisy private information about the fundamental value, the agents form different evaluations about heteroge…
Dependent MMD coresets help compare multiple related datasets.
problem Comparing multiple related datasets for insights into model generalization.
method Dependent MMD coresets for collections of datasets.
result Dependent MMD coresets facilitate comparison and understanding of multiple related datasets.
Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g. multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate…
SimCD simultaneously clusters cells and identifies differential gene expression in scRNA-seq data.
problem Separate clustering and differential expression analysis for scRNA-seq data leads to suboptimal results.
method Develops SimCD, a unified hierarchical gamma-negative binomial model for simultaneous cell clustering and differential expression analysis.
result SimCD outperforms existing methods in discovering cell clusters and capturing dynamic expression changes.
New methods detect unfairness in multiclass classifiers using DCP.
problem Detecting unfairness in multiclass classifiers.
method Generalizes DCP to multiclass, provides optimization methods.
result Detects classifiers treating a significant fraction of the population unfairly.
Understanding proper distance measures between distributions is at the core of several learning tasks such as generative models, domain adaptation, clustering, etc. In this work, we focus on mixture distributions that arise naturally in several application domains where the data contains different sub-populations. For …
Novel approach for robust domain generalization in health studies.
problem Challenges in making statistical inferences about underrepresented minority groups.
method Structured tensor completion for multi-dimensional domain generalization in linear regression models.
result Established rigorous theoretical guarantees and demonstrated minimax optimality.
The Web has enabled one of the most visible recent developments in education---the deployment of massive open online courses. With their global reach and often staggering enrollments, MOOCs have the potential to become a major new mechanism for learning. Despite this early promise, however, MOOCs are still relatively u…
ENN method uses expectile regression for genetic data analysis of complex diseases.
problem Discover additional genetic variants contributing to complex diseases.
method Developed an expectile neural network (ENN) method integrating expectile regression and neural networks.
result ENN method outperforms existing expectile regression in discovering genetic variants predisposing to sub-populations.
This work studies a stochastic optimal control problem for a pension scheme which provides an income-drawdown policy to its members after their retirement. To manage the scheme efficiently, the manager and members agree to share the investment risk based on a pre-decided risk-sharing rule. The objective is to maximise …
Study of entropy-regularized LQG MFGs with exploratory actions.
problem Optimizing multi-population mean field games with entropy regularization.
method Introduced exploratory actions and derived optimal action distributions.
result Optimal action distributions lead to ε-Nash equilibria in finite-population MFGs.
Method tackles missing covariates in large-scale datasets.
problem Cross-population missing data problem in large-scale datasets.
method Augmented transfer regression learning method combining importance-weighted estimating equations and imputation terms.
result Estimator is n1/2-consistent and asymptotically normal, attaining semiparametric efficiency bound under correct specification. Participants enrolled into randomized controlled trials (RCTs) often do not reflect real-world populations. Previous research in how best to translate RCT results to target populations has focused on weighting RCT data to look like the target data. Simulation work, however, has suggested that an outcome model approach …
Deep learning model creates patient representations for scalable EHR-based stratification.
problem Challenges in summarizing and representing patient data from EHRs prevent scalable stratification analysis.
method Unsupervised framework based on deep learning (ConvAE) using word embeddings, CNNs, and autoencoders.
result ConvAE significantly outperformed baselines in clustering diverse patient cohorts, identifying clinically relevant subtypes.
This article analyzes the problem of estimating the time until an event occurs, also known as survival modeling. We observe through substantial experiments on large real-world datasets and use-cases that populations are largely heterogeneous. Sub-populations have different mean and variance in their survival rates requ…
Unified study of stateful replay for streaming learning, reducing forgetting by 2-3x.
problem Catastrophic forgetting in streaming generative and predictive learning.
method Unified analysis of stateful replay for autoencoding, forecasting, and classification tasks.
result Stateful replay reduces average forgetting by a factor of 2-3 on heterogeneous multi-task streams.
The dearth of prescribing guidelines for physicians is one key driver of the current opioid epidemic in the United States. In this work, we analyze medical and pharmaceutical claims data to draw insights on characteristics of patients who are more prone to adverse outcomes after an initial synthetic opioid prescription…
Dimensionality reduction on Riemannian manifolds is challenging due to the complex nonlinear data structures. While probabilistic principal geodesic analysis~(PPGA) has been proposed to generalize conventional principal component analysis (PCA) onto manifolds, its effectiveness is limited to data with a single modality…
New criterion assesses cluster separability for validation.
problem Validating cluster analysis results and determining the number of clusters.
method Distinguishability criterion, combined loss function-based framework.
result Validated cluster configurations and determined the number of clusters.
A number of machine learning (ML) methods have been proposed recently to maximize model predictive accuracy while enforcing notions of group parity or fairness across sub-populations. We propose a desirable property for these procedures, slack-consistency: For any individual, the predictions of the model should be mono…
New approach to off-policy evaluation connects causal graph to policy effects.
problem Evaluating policies using observational data from different policies.
method Formalizes off-policy evaluation within a causal graph framework.
result Identifies specific causal estimands and highlights necessary experimental data.
Common fairness definitions in machine learning focus on balancing notions of disparity and utility. In this work, we study fairness in the context of risk disparity among sub-populations. We are interested in learning models that minimize performance discrepancies across sensitive groups without causing unnecessary ha…
Financial markets are often driven by latent factors which traders cannot observe. Here, we address an algorithmic trading problem with collections of heterogeneous agents who aim to perform optimal execution or statistical arbitrage, where all agents filter the latent states of the world, and their trading actions hav…
A lack of information exists about the health issues of lesbian, gay, bisexual, transgender, and queer (LGBTQ) people who are often excluded from national demographic assessments, health studies, and clinical trials. As a result, medical experts and researchers lack a holistic understanding of the health disparities fa…
As a mental disorder progresses, it may affect brain structure, but brain function expressed in brain dynamics is affected much earlier. Capturing the moment when brain dynamics express the disorder is crucial for early diagnosis. The traditional approach to this problem via training classifiers either proceeds from ha…
This work analyzes how users and services adapt to reduce risk, leading to specialization.
problem Adaptation of users and services to reduce risk affects learning and performance.
method Analyzed a class of dynamics where users allocate participation and services update parameters.
result Repeated myopic updates with multiple learners lead to better outcomes than repeated risk minimization.
The way that people make choices or exhibit preferences can be strongly affected by the set of available alternatives, often called the choice set. Furthermore, there are usually heterogeneous preferences, either at an individual level within small groups or within sub-populations of large groups. Given the availabilit…
With the aim of building machine learning systems that incorporate standards of fairness and accountability, we explore explicit subgroup sample complexity bounds. The work is motivated by the observation that classifier predictions for real world datasets often demonstrate drastically different metrics, such as accura…
Paper tackles fair low-rank approximation and column subset selection.
problem Minimize loss over sub-populations in machine learning.
method Developed algorithms for fair low-rank approximation and fair column subset selection.
result Achieved polynomial time algorithms for fair low-rank approximation.
MF-PID uses interacting samples to efficiently transport probability mass.
problem Efficiently transporting probability mass in generative models.
method Introducing Mean-Field Path-Integral Diffusion (MF-PID) where samples become interacting agents.
result MF-PID achieves 19-24% reductions in control energy for demand-response control of energy systems.
Firms implementing digital advertising campaigns face a complex problem in determining the right match between their advertising creatives and target audiences. Typical solutions to the problem have leveraged non-experimental methods, or used "split-testing" strategies that have not explicitly addressed the complexitie…
Integrates differential privacy and demographic parity in multi-class classification.
problem Ensuring fairness and privacy in sensitive applications.
method Designs DP2DP algorithm that enforces both demographic parity and differential privacy.
result DP2DP converges towards demographic parity at nearly the same rate as non-private methods, achieving state-of-the-art trade-offs.
SharedRep-RLHF learns shared traits for diverse groups, improving fairness and performance.
problem Uniform-reward RLHF fails to capture diverse preferences, leading to unfairness.
method SharedRep-RLHF learns shared traits among various groups, improving fairness and performance.
result SharedRep-RLHF outperforms MaxMin-RLHF by up to 20% in win rate.
This paper surveys fairness notions in ML and recommends the most suitable one for real-world scenarios.
problem Ensuring ML systems do not discriminate against specific individuals or sub-populations.
method Identifying fairness-related characteristics of real-world scenarios and analyzing the behavior of fairness notions.
result A decision diagram to recommend the most suitable fairness notion for specific setups.
Study laws of large numbers in online classification, determining optimal regret bounds.
problem Understanding how sequential sampling affects online learning and classification.
method Characterized online learnable classes and determined optimal regret bounds using Littlestone's dimension.
result Optimal regret bounds in online learning are determined, resolving open questions.