The paper addresses the problem of covariate mismatch in collaborative linear prediction, where different centers collect different sets of features. It proposes estimators that leverage information across centers under center-wise MCAR missingness, including a plug‑in estimator for low dimensions and an impute‑then‑regress strategy with ridge regularization for higher dimensions. All methods comply with federated learning constraints, exchanging only aggregated statistics, and the authors provide theoretical learning rates and numerical validation.
arXiv:2610.07292v1 Announce Type: cross Abstract: Missing covariates are frequently encountered in supervised learning problems, and classical methods for estimation using such data use carefully cho...
arXiv:2608. 15121v1 Announce Type: cross Abstract: Sufficient dimension reduction (SDR) seeks the minimal subspace of the predictors that captures the full conditional distribution of the response, which is known as the central subspace (CS).
Fed-ReMasker is a federated learning approach that adapts the ReMasker masked autoencoder for tabular data imputation, specifically addressing feature-level missingness where entire features are absent at some centers. The method enables centers to impute unobserved features by leveraging knowledge from collaborating institutions. In benchmark tests on synthetic and real-world datasets, Fed-ReMasker achieves the lowest imputation error in the majority of scenarios and remains robust to client heterogeneity, closely matching the performance of a centralized model.
arXiv:2605.04469v2 Announce Type: replace-cross Abstract: Large-scale population-level datasets, such as the UK Biobank and the All of Us Research Program, often lack covariates needed for a specific...
The paper introduces two hybrid imputation methods, NuclearForest and SoftForest, that combine a low‑rank initialization (using Singular Value Thresholding or SoftImpute) with a single Random Forest refinement. These methods capture global covariance patterns and local nonlinear dependencies, respectively, and are benchmarked against seven existing techniques across MCAR, MAR, and MNAR scenarios. Results show comparable or superior imputation accuracy to state‑of‑the‑art iterative methods while achieving significant speedups of roughly 5.8× and 9.5× over MissForest.
Missing data are a fundamental challenge in statistical analysis and machine learning, as the choice of imputation method substantially impacts downstream inference. In this work, we propose two hybri...
arXiv:2609.24086v1 Announce Type: cross Abstract: Large-scale multipurpose cohort studies and biobanks often omit covariates needed for specific downstream analyses. We study target-population infere...
In federated averaging, local objectives can admit multiple optimal heads, making the aggregate depend on which heads clients return. We study this ambiguity in federated multivariate regression with...
arXiv:2412. 18081v3 Announce Type: replace-cross Abstract: We study Heterogeneous Transfer Learning (HTL) for high-dimensional regression with differing feature sets.
The paper investigates Partial Least Squares (PLS) in high-dimensional settings, focusing on a model where two data matrices share a low-rank latent structure plus individual-specific components. By analyzing the singular vectors of the cross‑covariance matrix with random matrix theory, the authors derive asymptotic characterizations of how well the estimated latent directions align with the true ones. They show that the PLS variant based on Singular Value Decomposition (PLS‑SVD) outperforms separate principal component analysis in detecting the common latent subspace, while also identifying regimes where PLS‑SVD behaves counter‑intuitively or reaches fundamental limits.
arXiv:2602.01437v2 Announce Type: replace-cross Abstract: The problem of corrupted data, missing features, or missing modalities continues to plague the modern machine learning landscape. To address...
arXiv:2607. 07725v1 Announce Type: cross Abstract: Genomic prediction models often fail to transfer across institutions because sequencing panels differ across sites, creating structural feature missingness at deployment.