paper-with-me

Papers

Kernel Conjugate Gradient Methods with Random Projections

2018-11-05 · Junhong Lin, Volkan Cevher

We propose and study kernel conjugate gradient methods (KCGM) with random projections for least-squares regression over a separable Hilbert space. Considering two types of random projections generated by randomized sketches and Nystr\"{o}m subsampling, we prove optimal statistical results with respect to variants of norms for the algorithms under a suitable stopping rule. Particularly, our results show that if the projection dimension is proportional to the effective dimension of the problem, KCGM with randomized sketches can generalize optimally, while achieving a computational advantage. As a corollary, we derive optimal rates for classic KCGM in the well-conditioned regimes for the case that the target function may not be in the hypothesis space.

📄 PDF Abstract BibTeX arXiv:1811.01760

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Conjugate Gradients for Kernel Machines

2019-11-14 · Simon Bartels, Philipp Hennig

Regularized least-squares (kernel-ridge / Gaussian process) regression is a fundamental algorithm of statistics and machine learning. Because generic algorithms for the exact solution have cubic complexity in the number …

BIG-bench Machine Learningregression

Preconditioning Kernel Matrices

2016-02-22 · Kurt Cutajar, Michael A. Osborne, John P. Cunningham, Maurizio Filippone

The computational and storage complexity of kernel machines presents the primary barrier to their scaling to large, modern, datasets. A common way to tackle the scalability issue is to use the conjugate gradient algorith…

Convergence rates of Kernel Conjugate Gradient for random design regression

2016-07-08 · Gilles Blanchard, Nicole Krämer

We prove statistical rates of convergence for kernel-based least squares regression from i.i.d. data using a conjugate gradient algorithm, where regularization against overfitting is obtained by early stopping. This meth…

Dimensionality ReductionregressionSupervised dimensionality reduction

Diverse Exploration via Conjugate Policies for Policy Gradient Methods

2019-02-10 · Andrew Cohen, Xingye Qiao, Lei Yu, Elliot Way 외

We address the challenge of effective exploration while maintaining good performance in policy gradient methods. As a solution, we propose diverse exploration (DE) via conjugate policies. DE learns and deploys a set of c…

Policy Gradient Methods

Deterministic equivalent of the Conjugate Kernel matrix associated to Artificial Neural Networks

2023-06-09 · Clément Chouard

We study the Conjugate Kernel associated to a multi-layer linear-width feed-forward neural network with random weights, biases and data. We show that the empirical spectral distribution of the Conjugate Kernel converges …