arXiv research

Kernel ridge regression imputation with consistent variance estimation for handling missing data.

In this paper, we propose a random projection approach to estimate variance in kernel ridge regression. Our approach leads to a consistent estimator of the true variance, while being computationally more efficient. Our variance estimator is optimal for a large family of kernels, including cubic splines and Gaussian ker…

We improve kernel ridge regression for skewed responses using oversampling and adaptive partitioning.

The paper develops methods to handle missing data using regularized M-estimation in reproducing kernel Hilbert space.

New kernel methods estimate complex causal relationships.

We study the problem of estimating the ridges of a density function. Ridge estimation is an extension of mode finding and is useful for understanding the structure of a density. It can also be used to find hidden structure in point cloud data. We show that, under mild regularity conditions, the ridges of the kernel den…

New method quantifies uncertainty in distributed regression.

We establish optimal convergence rates for a decomposition-based scalable approach to kernel ridge regression. The method is simple to describe: it randomly partitions a dataset of size N into m subsets of equal size, computes an independent kernel ridge regression estimator for each subset, then averages the local sol…

Optimal CATE estimation with structured contrast functions using KRR.

Kernel ridge regression inference for nonstandard data.

ParK efficiently solves kernel ridge regression for large datasets.

Kernel ridge regression for causal inference with missing data.

Develops a method for kernel ridge regression under covariate shift using pseudo-labels.

This paper tackles the problem of selecting among several linear estimators in non-parametric regression; this includes model selection for linear regression, the choice of a regularization parameter in kernel ridge regression, spline smoothing or locally weighted regression, and the choice of a kernel in multiple kern…

Develops UKP for comparing feature representations in multitask learning.

This paper carries out a large dimensional analysis of a variation of kernel ridge regression that we call \emph{centered kernel ridge regression} (CKRR), also known in the literature as kernel ridge regression with offset. This modified technique is obtained by accounting for the bias in the regression problem resulti…

Proposes estimators for complex dose-response curves using kernel methods.

SQUEAK reduces space complexity for Nystrom approximations in KRR.

Kernel $ε$-Greedy optimizes multi-armed bandits with covariates for sub-linear regret.

Kernel balancing weights are generalized as KRRR, providing better confidence intervals for treatment effects.

Paper bounds the minimal rank for kernel ridge regression approximations.

Estimates KRR risk from training data for various kernels and hyperparameters.

The paper proves a non-asymptotic test error approximation for KRR.

Novel algorithm identifies nonlinear Granger causal relationships using kernel ridge regression.

Method estimates treatment effects with continuous values, correcting for confounding.

New estimator for estimating derivatives in nonparametric regression.

HKRR adapts to MIM, overcoming the curse of dimensionality.

Improves kernel ridge regression by optimizing scale and feature parameters.

Simplified kernel ridge regression with a conservation law.

Framework for transferring discount curve estimates across fixed-income product classes.

Paper proves convergence rates for Gaussian kernel ridge regression.

Study the cost of overfitting in noisy KRR models.

Tuning parameter selection is of critical importance for kernel ridge regression. To this date, data driven tuning method for divide-and-conquer kernel ridge regression (d-KRR) has been lacking in the literature, which limits the applicability of d-KRR for large data sets. In this paper, by modifying the Generalized Cr…

Improved kernel ridge regression for large datasets using weighted random binning.

The paper extends kernel ridge regression to product kernels and reveals new convergence behaviors.

pGMM kernel outperforms ordinary ridge regression and RBF kernel ridge regression without tuning.

Enhances supervised learning speed with KT algorithm.

Sharp bounds derived for test error of finite-rank kernel ridge regression.

A new method for faster bandwidth selection in Gaussian kernel ridge regression.

Paper analyzes distributed learning with non-i.i.d. samples.

New method for causal inference with complex treatment compositions.

Needlets have been recognized as state-of-the-art tools to tackle spherical data, due to their excellent localization properties in both spacial and frequency domains. This paper considers developing kernel methods associated with the needlet kernel for nonparametric regression problems whose predictor variables are de…

Many machine learning problems can be formulated as predicting labels for a pair of objects. Problems of that kind are often referred to as pairwise learning, dyadic prediction or network inference problems. During the last decade kernel methods have played a dominant role in pairwise learning. They still obtain a stat…

In this paper, we propose a variable selection method for general nonparametric kernel-based estimation. The proposed method consists of two-stage estimation: (1) construct a consistent estimator of the target function, (2) approximate the estimator using a few variables by l1-type penalized estimation. We see that the…

In this paper, we investigate a divide and conquer approach to Kernel Ridge Regression (KRR). Given n samples, the division step involves separating the points based on some underlying disjoint partition of the input space (possibly via clustering), and then computing a KRR estimate for each partition. The conquering s…

Improves regression efficiency by separating material and immaterial parts of responses.

Perturbation theory improves nonparametric instrumental variable estimation accuracy.

Two methods solve kernel ridge regression problems efficiently.