paper-with-me

Papers

ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions

2021-06-23 · NeurIPS 2021 12 · Luigi Carratino, Stefano Vigogna, Daniele Calandriello, Lorenzo Rosasco

We introduce ParK, a new large-scale solver for kernel ridge regression. Our approach combines partitioning with random projections and iterative optimization to reduce space and time complexity while provably maintaining the same statistical accuracy. In particular, constructing suitable partitions directly in the feature space rather than in the input space, we promote orthogonality between the local estimators, thus ensuring that key quantities such as local effective dimension and bias remain under control. We characterize the statistical-computational tradeoff of our model, and demonstrate the effectiveness of our method by numerical experiments on large-scale datasets.

📄 PDF Abstract BibTeX arXiv:2106.12231

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

On Kernel Derivative Approximation with Random Fourier Features

2018-10-11 · Zoltan Szabo, Bharath K. Sriperumbudur

Random Fourier features (RFF) represent one of the most popular and wide-spread techniques in machine learning to scale up kernel algorithms. Despite the numerous successful applications of RFFs, unfortunately, quite lit…

Ridgeless Regression with Random Features

2022-05-01 · Jian Li, Yong liu, Yingying Zhang

Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization. In this paper, we investigate the statistical properties of ridgeless …

regression

Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees

2018-04-26 · ICML 2017 8 · Haim Avron, Michael Kapralov, Cameron Musco, Christopher Musco 외

Random Fourier features is one of the most popular techniques for scaling up kernel methods, such as kernel ridge regression. However, despite impressive empirical results, the statistical properties of random Fourier fe…

regression

Kernel Ridge Riesz Representers: Generalization, Mis-specification, and the Counterfactual Effective Dimension

2021-02-22 · Rahul Singh

Kernel balancing weights provide confidence intervals for average treatment effects, based on the idea of balancing covariates for the treated group and untreated group in feature space, often with ridge regularization. …

counterfactualLearning Theoryregression

Scaling up Kernel Ridge Regression via Locality Sensitive Hashing

2020-03-21 · Michael Kapralov, Navid Nouri, Ilya Razenshteyn, Ameya Velingker 외

Random binning features, introduced in the seminal paper of Rahimi and Recht (2007), are an efficient method for approximating a kernel matrix using locality sensitive hashing. Random binning features provide a very simp…

Gaussian Processesregression