AI Theory

This paper presents efficient algorithms for Bayesian persuasion under approximate best response, offering polynomial-time solutions for specific cases and a quasi-polynomial-time approximation scheme…

Novel compositional PAC-Bayes framework delivers data-dependent generalization bounds for persistence-enhanced Graph Neural Networks, improving model design and performance.

Researchers developed a novel method using mechanistic interpretability to create compact formal proofs for AI model performance, improving AI safety and reliability.

Node2Vec, a popular network embedding method, is proven to consistently recover community structure in stochastic block models, paving the way for more reliable unsupervised community detection.

This paper presents communication-efficient protocols for the distributed experts problem, achieving near-optimal regret with theoretical and empirical validation.

A novel Collaborative Neural Framework (CNF) enhances the robustness of neural vehicle routing methods against adversarial attacks by collaboratively training multiple models and intelligently distrib…

New method for eigenvector estimation achieves optimal rates without coherence dependence, improving low-rank matrix denoising and related tasks.

LeTCC: A novel learning-theoretic framework for resilient distributed computing, achieving faster convergence and higher accuracy than existing methods by integrating learning theory principles with c…

Researchers strengthen understanding of transformer self-attention by proving asymptotic convergence to single clusters under causal masking, linking it to the Rényi parking problem.

Zero-shot learning models often fail in real-world scenarios due to unseen class distribution shifts. This work introduces a novel algorithm that learns robust representations by creating synthetic d…

ChronoEpilogi efficiently finds all minimal sets of time-series variables optimally predicting a target, improving forecasting while providing crucial insights for knowledge discovery and causal model…

Researchers developed novel algorithms to generate structurally diverse graphs, improving graph algorithm testing and neural network evaluation.

Accelerate DEQ certification up to 7x with Serialized Random Smoothing (SRS), achieving certified robustness on large-scale datasets without sacrificing accuracy.

This paper introduces a novel machine unlearning method using projected noisy stochastic gradient descent, providing the first approximate unlearning guarantee under convexity, significantly improving…

CausalDiff leverages causal inference and diffusion models to create a robust AI defense against unseen adversarial attacks, significantly outperforming state-of-the-art methods.

Causal assumptions drastically alter predictor merging, with CMAXENT revealing logistic regression for causal and LDA for anticausal directions.

CtrlNS: A novel framework for causal temporal representation learning tackles the challenge of nonstationary time series by leveraging sparse transition assumptions, achieving improved accuracy in ide…

Researchers introduce a non-parametric causal inference framework to analyze closed-loop optogenetics designs, revealing previously hidden causal effects of neural circuit manipulations on behavior.

This paper introduces a novel algorithm to accurately compute causal effects within specific sub-populations, even when hidden factors influence the data, advancing causal inference significantly.

CASCADE algorithm unveils hidden causal structures in event sequences by minimizing description length, surpassing existing Granger causality-based methods.