paper-with-me

홈 › Papers

Scaling Neural Tangent Kernels via Sketching and Random Features

2021-06-15 · NeurIPS 2021 12 · Amir Zandieh, Insu Han, Haim Avron, Neta Shoham, Chaewon Kim, Jinwoo Shin

The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely-wide neural networks trained under least squares loss by gradient descent. Recent works also report that NTK regression can outperform finitely-wide neural networks trained on small-scale datasets. However, the computational complexity of kernel methods has limited its use in large-scale learning tasks. To accelerate learning with NTK, we design a near input-sparsity time approximation algorithm for NTK, by sketching the polynomial expansions of arc-cosine kernels: our sketch for the convolutional counterpart of NTK (CNTK) can transform any image using a linear runtime in the number of pixels. Furthermore, we prove a spectral approximation guarantee for the NTK matrix, by combining random features (based on leverage score sampling) of the arc-cosine kernels with a sketching algorithm. We benchmark our methods on various large-scale regression and classification tasks and show that a linear regressor trained on our CNTK features matches the accuracy of exact CNTK on CIFAR-10 dataset while achieving 150x speedup.

📄 PDF Abstract BibTeX arXiv:2106.07880

Code (1)

insuhan/ntk-sketch-rf 공식 구현 pytorch

Tasks

ARCregression

Methods 이 논문이 사용한 방법론

NTK 설명 없음

Similar Papers 제목 키워드 기반

Learning with Neural Tangent Kernels in Near Input Sparsity Time

2021-04-01 · Amir Zandieh

The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely wide neural nets trained under least squares loss by gradient descent. However, despite its importance, the super-quadratic runtime of kernel metho…

ARC

Random Features for the Neural Tangent Kernel

2021-04-03 · Insu Han, Haim Avron, Neta Shoham, Chaewon Kim 외

The Neural Tangent Kernel (NTK) has discovered connections between deep neural networks and kernel methods with insights of optimization and generalization. Motivated by this, recent works report that NTK can achieve bet…

ARC

A Simple Algorithm For Scaling Up Kernel Methods

2023-01-26 · Teng Andrea Xu, Bryan Kelly, Semyon Malamud

The recent discovery of the equivalence between infinitely wide neural networks (NNs) in the lazy training regime and Neural Tangent Kernels (NTKs) (Jacot et al., 2018) has revived interest in kernel methods. However, co…

regression

Fast Sketching of Polynomial Kernels of Polynomial Degree

2021-08-21 · Zhao Song, David P. Woodruff, Zheng Yu, Lichen Zhang

Kernel methods are fundamental in machine learning, and faster algorithms for kernel approximation provide direct speedups for many core tasks in machine learning. The polynomial kernel is especially important as other k…

ARCBIG-bench Machine Learning

Meta-Principled Family of Hyperparameter Scaling Strategies

2022-10-10 · Sho Yaida

In this note, we first derive a one-parameter family of hyperparameter scaling strategies that interpolates between the neural-tangent scaling and mean-field/maximal-update scaling. We then calculate the scalings of dyna…

Representation Learning