AI Theory

Forgetful algorithms are essential for fast last-iterate convergence in learning games; otherwise, even popular methods like OMWU fail.

Polar codes revolutionize channel simulation, offering scalable, high-performance schemes that significantly outperform existing methods.

FairWire tackles structural bias in graph machine learning, proposing a novel fairness regularizer and a fair graph generation framework for unbiased link prediction and graph generation.

Fairness-aware estimation of graphical models (GMs) tackles bias in GM estimations by integrating graph disparity error and a tailored loss function into multi-objective optimization, effectively miti…

FairnessWithoutHarm achieves fairer ML models without sacrificing accuracy by using an influence-guided active sampling method that doesn’t require sensitive training data.

Fairness in social influence maximization is achieved via optimal transport, optimizing both outreach and a new ‘mutual fairness’ metric that considers variability in outreach scenarios.

First non-wasteful algorithm achieving 1/2-approximation for class envy-freeness, class proportionality, and utilitarian social welfare in online class matching.

Fair Wasserstein Coresets (FWC) efficiently generates fair, representative subsets of large datasets for downstream machine learning tasks, improving fairness and utility.

Fair algorithms can leverage biased predictions to improve performance while guaranteeing fairness for all candidates.

This paper proposes a novel online bilateral trading algorithm maximizing the fair gain from trade and provides tight regret bounds under various settings.

Fair GLASSO ensures fair Gaussian graphical models by introducing novel bias metrics and a penalized maximum likelihood estimator to mitigate group biases in data.

FairBiNN, a novel bilevel neural network, achieves Pareto optimal solutions by simultaneously optimizing for accuracy and fairness, outperforming existing methods.

This paper presents novel, scalable algorithms for fair and efficient constrained resource allocation under uncertainty using robust and CVaR optimization.

This paper presents optimal fair mechanisms for dynamic auction design, maximizing seller revenue while guaranteeing minimum allocations to multiple buyer groups.

Researchers reveal a high risk of training data extraction from molecular pre-trained models, challenging the assumption that model sharing alone adequately protects against data theft.

This paper introduces a novel nonparametric method to make policy evaluations from randomized trials externally valid, even when trial and target populations differ. It leverages additional covariate…

VIJI, a novel second-order algorithm, achieves optimal convergence rates for variational inequalities even with inexact Jacobian information, bridging the gap between theory and practice in machine le…

Deep state space models (SSMs) gain adversarial robustness through an adaptive scaling mechanism, improving performance without overfitting issues.

Eigen-SAM significantly boosts generalization in deep learning by directly addressing SAM’s limitations through explicit top Hessian eigenvalue regularization.

New method, STRIPE-X, powerfully detects ’encoding’ in AI explanations—a sneaky phenomenon where explanations predict outcomes better than their constituent parts alone would suggest.