Winner take all in SVM?

1 min read

updated: 2010/01/05, add plot of original data

Assume our data contains two features and they are highly correlated (say, r>0.9). The 1st feature does slightly better than the 2nd one in classifying the data. The question is, is the weight of the 2nd feature close to 0, or close to the weight of 1st feature?

If this is a linear regression, we know the winner (1st feature) will take all — the beta value for the 2nd feature will be close to 0. But in linear SVM, the weight for the 2nd feature seems close to the weight of 1st feature.

Here is the result of simulation. In this simulation, feature 1 classify the data well (97% accuracy). The 2nd feature is simply the 1st feature plus different amount of noise. We can see that when feature 1 and feature 2 are highly correlated, their weights are close in SVM. But in linear regression the weight of the 2nd feature remains close to 0 b/c it doesn’t add any classification power in addition to feature 1.


Updated: original data plot with different correlation

The data are generated this way:

N = 500;
l = [ones(N,1); -ones(N,1)]; % label
d = [];
d(:,1) = l + randn(2*N,1)/2;
d(:,2) = sign(rho)*d(:,1) + randn(2*N,1)/10*rho;
d = normalize(d);

rho is a parameter controlling the amount of noise added to the 2nd component. Its range is between -100 to 100. Note data is normalized (so all data point are between 0 and 1) prior to further analysis (SVM or linear regression).

For SVM, I use libsvm 2.89 MatLab version. I used linear SVM with C=1.
For linear regression, I simply use the most naive method:
beta = inv(X'*X)*X'*Y;


Want to receive new post notification? 有新文章通知我


作者:北京师范大学 龙宇航,[email protected]代码来源(见本页底部):周思远 在使用wtc计算脑间神经同步后,我们需要在多个频率段、多个通道组合上对神经同步值进行统计检验,因
Xu Cui
1 min read

Calculate phase difference between two general signals (e.g. HbO…

In a recent fNIRS journal club (vedio recorded here), Dr. Tong talked about their work on the phase difference between oxy and deoxy Hb, and its relationship with participants’ age. This article is a demo of how to use Hilbert transform to calc
Xu Cui
1 min read

nirs2img, create an image file from NIRS data

Update 2021/2/27: If you find griddata3 not working, try to change griddata3 to griddata. I was asked where to get nirs2img script. Here it is. The download link is at the bottom of this article. nirs2img is to create an image file from the input dat
Xu Cui
51 sec read

2 Replies to “Winner take all in SVM?”

  1. It’s very interesting to see the tendency in SVM results plot, esp. when the correlation is low. Since that means the distribution of your data is more spherical than elliptical, but the high ratio between the two weights means the support vectors are located at sides of two distributed ‘clouds’, even their centers might be located diagonally. In the case of linear regression, supposing you used a direct glm solution (or regularized solving procedure?), I would expect a big variance when the two feature components are highly correlated, as the covariance matrix is almost singular (a strong regularization should lead to results similar to the svm case though).

    It would be really nice to see more detail about your experiment setting, including data generation and parameters used in two analyses.

Leave a Reply

Your email address will not be published. Required fields are marked *