On the Equivalence between Neural Network and Support Vector Machine

11/11/2021
by   Yilan Chen, et al.
12

Recent research shows that the dynamics of an infinitely wide neural network (NN) trained by gradient descent can be characterized by Neural Tangent Kernel (NTK) <cit.>. Under the squared loss, the infinite-width NN trained by gradient descent with an infinitely small learning rate is equivalent to kernel regression with NTK <cit.>. However, the equivalence is only known for ridge regression currently <cit.>, while the equivalence between NN and other kernel machines (KMs), e.g. support vector machine (SVM), remains unknown. Therefore, in this work, we propose to establish the equivalence between NN and SVM, and specifically, the infinitely wide NN trained by soft margin loss and the standard soft margin SVM with NTK trained by subgradient descent. Our main theoretical results include establishing the equivalence between NN and a broad family of ℓ_2 regularized KMs with finite-width bounds, which cannot be handled by prior work, and showing that every finite-width NN trained by such regularized loss functions is approximately a KM. Furthermore, we demonstrate our theory can enable three practical applications, including (i) non-vacuous generalization bound of NN via the corresponding KM; (ii) non-trivial robustness certificate for the infinite-width NN (while existing robustness verification methods would provide vacuous bounds); (iii) intrinsically more robust infinite-width NNs than those from previous kernel regression. Our code for the experiments are available at <https://github.com/leslie-CH/equiv-nn-svm>.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/22/2021

Weighted Neural Tangent Kernel: A Generalized and Improved Network-Induced Kernel

The Neural Tangent Kernel (NTK) has recently attracted intense study, as...
research
06/11/2021

Neural Optimization Kernel: Towards Robust Deep Learning

Recent studies show a close connection between neural networks (NN) and ...
research
12/06/2019

A priori generalization error for two-layer ReLU neural network through minimum norm solution

We focus on estimating a priori generalization error of two-layer ReLU n...
research
08/02/2021

Deep Stable neural networks: large-width asymptotics and convergence rates

In modern deep learning, there is a recent and growing literature on the...
research
06/23/2022

Measuring Representational Robustness of Neural Networks Through Shared Invariances

A major challenge in studying robustness in deep learning is defining th...
research
06/17/2022

Fast Finite Width Neural Tangent Kernel

The Neural Tangent Kernel (NTK), defined as Θ_θ^f(x_1, x_2) = [∂ f(θ, x_...
research
10/19/2019

Neural Spectrum Alignment

Expressiveness of deep models was recently addressed via the connection ...

Please sign up or login with your details

Forgot password? Click here to reset