Nonconvex projected gradient descent for noisy inductive matrix completion achieves linear convergence and order-optimal error at sample complexity scaling with side-information dimension a instead of ambient dimension n.
Annals of the Institute of Statistical Mathematics , volume=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
A methodological framework for separable effects analysis that distinguishes four-arm and two-arm designs, with EIF-based estimation and falsification tests.
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
A doubly robust, asymptotically normal estimator for regression with completely missing covariates across populations, combining importance weighting and moment imputation under a sub-population shift assumption.
Clipped least-squares importance fitting enables weighted conformal prediction to achieve dataset-conditional coverage guarantees under unbounded covariate shifts by bounding undercoverage and estimating a corrective inflation factor from data.
citing papers explorer
-
Sample efficient inductive matrix completion with noise and inexact side information
Nonconvex projected gradient descent for noisy inductive matrix completion achieves linear convergence and order-optimal error at sample complexity scaling with side-information dimension a instead of ambient dimension n.
-
Separable Effects in Four-Arm and Two-Arm Designs
A methodological framework for separable effects analysis that distinguishes four-arm and two-arm designs, with EIF-based estimation and falsification tests.
-
Adaptive Kernel Ridge Regression with Linear Structure: Sharp Oracle Inequalities and Minimax Optimality
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
-
Augmented transfer regression learning for completely missing covariates
A doubly robust, asymptotically normal estimator for regression with completely missing covariates across populations, combining importance weighting and moment imputation under a sub-population shift assumption.
-
Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shifts
Clipped least-squares importance fitting enables weighted conformal prediction to achieve dataset-conditional coverage guarantees under unbounded covariate shifts by bounding undercoverage and estimating a corrective inflation factor from data.