Archives AI News

Deep P-Spline: Theory, Fast Tuning, and Application

arXiv:2501.01376v1 Announce Type: cross Abstract: Deep neural networks (DNNs) have been widely applied to solve real-world regression problems. However, selecting optimal network structures remains a significant challenge. This study addresses this issue by linking neuron selection in DNNs to knot…

Two-Stage Nuisance Function Estimation for Causal Mediation Analysis

arXiv:2404.00735v3 Announce Type: replace-cross Abstract: Tchetgen Tchetgen and Shpitser (2012) introduced an efficient, debiased, and robust influence function-based estimator for the mediation functional, which is the key component in mediation analysis. This estimator relies on the treatment, mediator, and outcome…

On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms

arXiv:2509.25126v1 Announce Type: new Abstract: We study spectral learning for orthogonally decomposable (odeco) tensors, emphasizing the interplay between statistical limits, optimization geometry, and initialization. Unlike matrices, recovery for odeco tensors does not hinge on eigengaps, yielding improved robustness under noise.…

Symmetry-Aware Bayesian Optimization via Max Kernels

arXiv:2509.25051v1 Announce Type: new Abstract: Bayesian Optimization (BO) is a powerful framework for optimizing noisy, expensive-to-evaluate black-box functions. When the objective exhibits invariances under a group action, exploiting these symmetries can substantially improve BO efficiency. While using maximum similarity across…

CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk

arXiv:2507.08150v2 Announce Type: replace Abstract: Existing methods typically address either aleatoric uncertainty due to measurement noise or epistemic uncertainty resulting from limited data, but not both in a balanced manner. We propose CLEAR, a calibration method with two distinct parameters,…

Inductive Bias and Spectral Properties of Single-Head Attention in High Dimensions

arXiv:2509.24914v1 Announce Type: new Abstract: We study empirical risk minimization in a single-head tied-attention layer trained on synthetic high-dimensional sequence tasks, given by the recently introduced attention-indexed model. Using tools from random matrix theory, spin-glass physics, and approximate message passing,…