AI Theory

This paper presents novel graphical criteria and estimators for accurately evaluating policy effectiveness across multiple experimental datasets, even when data distributions differ.

Efficient algorithm achieves near-perfect graph matching in correlated stochastic block models, resolving a key open problem and enabling improved community detection.

Heat Diffusion Optimization (HeO) framework efficiently solves combinatorial optimization problems by enabling information propagation through heat diffusion, outperforming existing methods.

Efficiently and privately reconstructing marginal queries from noisy data using residuals improves accuracy of existing differential privacy mechanisms.

New efficient algorithms minimize regret in extensive-form games by cleverly using low-degree swap deviations and a relaxed fixed-point concept, improving correlated equilibrium computation.

First-price auction efficiency in autobidding plummets to 45.7% with mixed bidders, but machine-learned advice restores optimality.

ECLipsE: A novel compositional approach drastically accelerates Lipschitz constant estimation for deep neural networks, achieving speedups of thousands of times compared to the state-of-the-art while …

This research introduces novel algorithms to dynamically price third-party platform service fees under strategic buyer behavior, achieving optimal revenue with a theoretically proven regret bound.

Repeated cake-cutting game reveals that strategic players can exploit myopic opponents, but equitable outcomes are achievable through specific strategies.

Dual-Perspective Activation (DPA) efficiently denoises ANN channels by jointly using forward and backward propagation criteria, improving sparsity and accuracy.

Dual Lagrangian Learning (DLL) revolutionizes conic optimization by leveraging machine learning to efficiently learn high-quality dual-feasible solutions, achieving 1000x speedups over traditional sol…

SGA: A novel framework boosts Signed Graph Neural Network performance by addressing graph sparsity and unbalanced triangles, achieving up to 26.2% F1-micro improvement.

DRAGO: A novel primal-dual algorithm delivers faster, state-of-the-art convergence for distributionally robust optimization.

DOPPLER, a novel low-pass filter, significantly enhances differentially private (DP) optimizer performance by reducing the impact of privacy noise, bridging the gap between DP and non-DP training.

Causal inference revolutionized: New framework estimates causal effects from exchangeable data, enabling simultaneous causal discovery and effect estimation via the Do-Finetti algorithm.

Divide-and-conquer predictive coding (DCPC) revolutionizes structured Bayesian inference by achieving superior performance in high-dimensional problems while remaining biologically plausible.

Training robust cooperative AI agents requires diverse and specialized training partners, but existing methods often produce overfit partners. This paper proposes novel methods using reinforcement and…

DISTRICTNET: A novel decision-aware learning approach drastically cuts geographical districting costs by integrating combinatorial optimization and graph neural networks.

This research introduces distributionally robust performative prediction, offering a new solution concept (DRPO) that minimizes performative risk even with misspecified distribution maps, ensuring rob…

This paper provides the first statistical learning guarantees for distributional regression using CRPS, offering concentration bounds for model fitting, selection, and convex aggregation, applicable t…