The paper introduces a method called Surrogate Graph Partitioning for Spatial Prediction, which constructs spatial segments by minimizing within-segment prediction variance. The assignment of points to segments is framed as a mixed‑integer quadratic programming problem, but due to its high computational cost, an approximation scheme based on graph partitioning properties is proposed. Experiments show that this approximation efficiently identifies spatial segments.
arXiv:2608. 14968v1 Announce Type: cross Abstract: We consider nonparametric regression when the association between a response and its covariates changes across an unknown partition of a spatial domain.
arXiv:2503. 12902v4 Announce Type: replace Abstract: Model trees provide an appealing way to perform interpretable machine learning for both classification and regression problems.
The paper introduces the twoblock clustering tree (TBTREE), a deterministic regression tree designed for multivariate responses that uses local multivariate linear models as leaves and incorporates dense or sparse twoblock dimension reduction both in the leaf models and impurity calculation. TBTREE aims to provide an interpretable, regime‑aligned piecewise‑linear description of data while maintaining predictive performance through a split/leaf decoupling strategy. Additionally, the authors propose a coskewness‑based estimator for the twoblock reduced space to identify non‑normal clusters, demonstrating the method’s ability to recover piecewise linear regimes in simulations and to model complex nonlinear dependencies in real‑world datasets, achieving performance comparable to black‑box techniques such as random forests.
arXiv:2507. 02921v4 Announce Type: replace-cross Abstract: Learning effective representations of urban environments requires capturing spatial structure beyond fixed administrative boundaries.
arXiv:2604. 07635v2 Announce Type: replace-cross Abstract: This research considers a scalable inference for spatial data modeled through Gaussian intrinsic conditional autoregressive (ICAR) structures.
arXiv:2609.36046v1 Announce Type: cross Abstract: In spatial observational studies, treatment assignment and outcomes often exhibit spatial dependence patterns, and treatment effects may vary across...
arXiv:2603.05575v2 Announce Type: replace-cross Abstract: We study prediction-powered conditional inference in the setting where labeled data are scarce, unlabeled covariates are abundant, and a blac...
The paper introduces a look‑ahead splitting rule for Classification and Regression Trees (CART) that evaluates candidate splits by the error reduction achieved after growing a conventional CART subtree beneath each split. To keep the method computationally feasible, a smart look‑ahead algorithm is proposed that learns downstream split values from node‑level features. Experiments on simulated data and two real datasets show that both full and smart look‑ahead methods outperform the standard greedy splitting strategy, especially in hierarchical or interaction‑driven scenarios.
arXiv:2609.15305v1 Announce Type: cross Abstract: Urban region representation learning commonly combines heterogeneous data sources, such as mobility flows, points of interest, and land-use informati...
The paper introduces a divide-and-conquer neural Bayes estimation framework for spatial and spatiotemporal point process models. It uses transformer-based architectures on partitions of the domain and an attention mechanism to combine local summaries, enabling direct inference from raw point pattern data. Simulation studies show reliable inference with better scalability than existing neural and classical likelihood-based methods, and the approach is applied to whale call data in Cape Cod Bay, producing parameter estimates and credible intervals at negligible cost after training.
arXiv:2609. 30477v1 Announce Type: cross Abstract: Exact Euclidean \(K\)-means partitions \(n\) observations into \(K\) unlabelled clusters, but the unrestricted search is generally exponential.
HealthMamba is an uncertainty‑aware spatiotemporal graph state space model designed to predict healthcare facility visits more accurately and reliably. It integrates a Unified Spatiotemporal Context Encoder, a novel GraphMamba module for hierarchical modeling, and a comprehensive uncertainty quantification component. Evaluated on large‑scale datasets from California, New York, Texas, and Florida, it improves prediction accuracy by about 6.0% and uncertainty quantification by 3.5% over state‑of‑the‑art baselines.