paper-with-me

홈 › Papers

Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width

2020-02-10 · Yu Bai, Ben Krause, Huan Wang, Caiming Xiong, Richard Socher

We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width. Taylorized training involves training the $k$-th order Taylor expansion of the neural network at initialization, and is a principled extension of linearized training---a recently proposed theory for understanding the success of deep learning. We experiment with Taylorized training on modern neural network architectures, and show that Taylorized training (1) agrees with full neural network training increasingly better as we increase $k$, and (2) can significantly close the performance gap between linearized and full training. Compared with linearized training, higher-order training works in more realistic settings such as standard parameterization and large (initial) learning rate. We complement our experiments with theoretical results showing that the approximation error of $k$-th order Taylorized models decay exponentially over $k$ in wide neural networks.

📄 PDF Abstract BibTeX arXiv:2002.04010

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Low Dimensional Explicit Feature Maps

2015-12-01 · ICCV 2015 12 · Ondrej Chum

Approximating non-linear kernels by finite-dimensional feature maps is a popular approach for speeding up training and evaluation of support vector machines or to encode information into efficient match kernels. We propo…

Katyusha Acceleration for Convex Finite-Sum Compositional Optimization

2019-10-24 · Yibo Xu, Yangyang Xu

Structured problems arise in many applications. To solve these problems, it is important to leverage the structure information. This paper focuses on convex problems with a finite-sum compositional structure. Finite-sum …

Stochastic Optimization

Trust-Region Algorithms for Training Responses: Machine Learning Methods Using Indefinite Hessian Approximations

2018-07-01 · Jennifer B. Erway, Joshua Griffin, Roummel F. Marcia, Riadh Omheni

Machine learning (ML) problems are often posed as highly nonlinear and nonconvex unconstrained optimization problems. Methods for solving ML problems based on stochastic gradient descent are easily scaled for very large …

BIG-bench Machine Learning

What can linearized neural networks actually say about generalization?

2021-06-12 · NeurIPS 2021 12 · Guillermo Ortiz-Jiménez, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

For certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization, but for the networks used in practice, the empirical NTK only provides a rough first-order approxima…

Can overfitted deep neural networks in adversarial training generalize? -- An approximation viewpoint

2024-01-24 · Zhongjie Shi, Fanghui Liu, Yuan Cao, Johan A. K. Suykens

Adversarial training is a widely used method to improve the robustness of deep neural networks (DNNs) over adversarial perturbations. However, it is empirically observed that adversarial training on over-parameterized ne…