AI Theory

Inspired by nature, researchers introduce a novel spatiotemporal local algorithm for machine learning that outperforms backpropagation in online learning scenarios with limited data or long video stre…

This paper proposes ’natural counterfactuals’ for more realistic counterfactual reasoning in AI, using backtracking to minimize deviations from observed data while ensuring feasibility.

Researchers introduce a novel approach to mutual information (MI) estimation using normalizing flows, providing accurate estimates even in high dimensions.

New algorithms conquer regret in multi-armed bandits challenged by network interference, achieving provably low regret with both known and unknown network structures.

Multilinear Mixture of Experts (μMoE) achieves scalable expert specialization in deep neural networks through tensor factorization, enabling efficient fine-tuning and interpretable model editing.

Unbounded label spaces conquered! New algorithm achieves optimal mistake bounds in multiclass transductive online learning.

This paper introduces a novel model for multi-winner reconfiguration, analyzing the computational complexity of transitioning between committees using four approval-based voting rules, demonstrating b…

Multi-group Proportional Representation (MPR) tackles skewed search results by measuring representation across intersectional groups, improving fairness in image retrieval.

In multi-agent imitation learning, achieving regret equivalence is harder than value equivalence; this paper introduces novel algorithms that efficiently minimize the regret gap under various assumpti…

Motif-oriented influence maximization tackles viral marketing’s challenge of reaching groups by proving a greedy algorithm with guaranteed approximation ratio and near-linear time complexity.

Adaptive greedy algorithms significantly improve the accuracy of identifying the most influential subset of training data, overcoming limitations of existing methods that fail to capture complex inter…

Algorithmic monoculture harms applicant selection and market efficiency; this paper introduces a model to analyze its effects in two-sided matching markets.

Counterfactual Clamping Attack (CCA) improves model reconstruction using counterfactual explanations by leveraging decision boundary proximity, offering theoretical guarantees and enhanced fidelity.

Training AI models on AI-generated data leads to performance degradation, known as model collapse. This paper offers analytical formulas that precisely quantify this effect in high-dimensional regress…

A new formula unifies lazy and active neural network training regimes, revealing a mixed regime that combines their strengths for faster convergence and low-rank bias.

DPR, a novel bias mitigation method, robustly improves model performance by leveraging disagreement probability without needing bias labels, achieving state-of-the-art results.

This paper presents novel mirror and preconditioned gradient descent algorithms for optimizing functionals over Wasserstein space, offering improved convergence and efficiency for various machine lear…

A novel lossy compression framework, Minimum Entropy Coupling with Bottleneck (MEC-B), extends existing methods by integrating a bottleneck for controlled stochasticity, enhancing performance in scen…

Data balancing in machine learning can hurt fairness and robustness; this paper reveals when and why, offering solutions for safer AI.

AI bias amplification in decision-making is uncovered, showing how fair prediction scores can become discriminatory after thresholding, urging stronger regulatory oversight.