Resubstitution loss for support vector machine regression model
L = resubLoss(mdl)
L = resubLoss(mdl,Name,Value)
returns the resubstitution loss for the support vector machine (SVM) regression model
L = resubLoss(
mdl, using the training data stored in
mdl.X and corresponding response values stored in
Specify optional pairs of arguments as
the argument name and
Value is the corresponding value.
Name-value arguments must appear after other arguments, but the order of the
pairs does not matter.
Before R2021a, use commas to separate each name and value, and enclose
Name in quotes.
to use the epsilon-insensitive loss function to compute the resubstitution
LossFun — Loss function
"mse" (default) |
"epsiloninsensitive" | function handle
Loss function, specified as
"epsiloninsensitive", or a function
The following table lists the available loss functions. Specify one using its corresponding value.
Specify your own function using function handle notation.
n = size(X,1)is the sample size. Your function must have the signature
lossvalue = lossfun(Y,Yfit,W), where:
The output argument
lossvalueis a numeric value.
You choose the function name (
Yis an n-by-1 numeric vector of observed response values.
Yfitis an n-by-1 numeric vector of predicted response values, calculated using the corresponding predictor values in
X(similar to the output of
Wis an n-by-1 numeric vector of observation weights.
Specify your function using
PredictionForMissingValue — Predicted response value to use for observations with missing predictor values
"median" (default) |
"omitted" | numeric scalar
Predicted response value to use for observations with missing predictor values,
"omitted", or a numeric scalar.
If an observation is missing all predictor values, an observed response value, or an
observation weight, then
resubLoss does not use the observation
in the loss computation.
L — Resubstitution loss
Resubstitution loss, returned as a scalar value.
The resubstitution loss is the loss calculated between the response training data and the model’s predicted response values based on the input training data.
Resubstitution loss can be an overly optimistic estimate of the predictive error on new data. If the resubstitution loss is high, the model’s predictions are not likely to be very good. However, having a low resubstitution loss does not guarantee good predictions for new data.
To better assess the predictive accuracy of your model, cross validate the model using
Resubstitution Loss for SVM Regression Model
This example shows how to train an SVM regression model, then calculate the resubstitution loss using mean square error (MSE) and epsilon-insensitive loss.
This example uses the abalone data from the UCI Machine Learning Repository. Download the data and save it in your current directory with the name
Read the data into a
tbl = readtable('abalone.data','Filetype','text', ... 'ReadVariableNames',false); rng default % for reproducibility
The sample data contains 4177 observations. All of the predictor variables are continuous except for
sex, which is a categorical variable with possible values
'M' (for males),
'F' (for females), and
'I' (for infants). The goal is to predict the number of rings on the abalone, and thereby determine its age, using physical measurements.
Train an SVM regression model to the data, using a Gaussian kernel function with an automatic kernel scale. Standardize the data.
mdl = fitrsvm(tbl,'Var9','KernelFunction','gaussian', ... 'KernelScale','auto','Standardize',true);
Calculate the resubstitution loss using mean square error (MSE).
mse_loss = resubLoss(mdl)
mse_loss = 4.0603
Calculate the epsilon-insensitive loss.
eps_loss = resubLoss(mdl,'LossFun','epsiloninsensitive')
eps_loss = 1.1027
Mean Squared Error
The weighted mean squared error is calculated as follows:
n is the number of rows of data
xj is the jth row of data
yj is the true response to xj
f(xj) is the response prediction of the SVM regression model
w is the vector of weights.
The weights in w are all equal to one by default. You can specify different values for weights using the
'Weights' name-value pair argument. If you specify weights, each value is divided by the sum of all weights, such that the normalized weights add to one.
Epsilon-Insensitive Loss Function
The epsilon-insensitive loss function ignores errors that are within the distance epsilon (ε) of the function value. It is formally described as:
The mean epsilon-insensitive loss is calculated as follows:
 Nash, W.J., T. L. Sellers, S. R. Talbot, A. J. Cawthorn, and W. B. Ford. "The Population Biology of Abalone (Haliotis species) in Tasmania. I. Blacklip Abalone (H. rubra) from the North Coast and Islands of Bass Strait." Sea Fisheries Division, Technical Report No. 48, 1994.
 Waugh, S. "Extending and Benchmarking Cascade-Correlation: Extensions to the Cascade-Correlation Architecture and Benchmarking of Feed-forward Supervised Artificial Neural Networks." University of Tasmania Department of Computer Science thesis, 1995.
 Clark, D., Z. Schreter, A. Adams. "A Quantitative Comparison of Dystal and Backpropagation." submitted to the Australian Conference on Neural Networks, 1996.
 Lichman, M. UCI Machine Learning Repository, [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.
Accelerate code by running on a graphics processing unit (GPU) using Parallel Computing Toolbox™. (since R2023a)
This function fully supports GPU arrays. For more information, see Run MATLAB Functions on a GPU (Parallel Computing Toolbox).
Version HistoryIntroduced in R2015b
R2023b: Specify predicted response value to use for observations with missing predictor values
Starting in R2023b, when you predict or compute the loss, some regression models allow you to specify the predicted response value for observations with missing predictor values. Specify the
PredictionForMissingValue name-value argument to use a numeric scalar, the training set median, or the training set mean as the predicted value. When computing the loss, you can also specify to omit observations with missing predictor values.
This table lists the object functions that support the
PredictionForMissingValue name-value argument. By default, the
functions use the training set median as the predicted response value for observations with
missing predictor values.
|Model Type||Model Objects||Object Functions|
|Gaussian process regression (GPR) model|
|Gaussian kernel regression model|
|Linear regression model|
|Neural network regression model|
|Support vector machine (SVM) regression model|
In previous releases, the regression model
predict functions listed above used
NaN predicted response values for observations with missing predictor values. The software omitted observations with missing predictor values from the resubstitution ("resub") and cross-validation ("kfold") computations for prediction and loss.
R2023a: GPU array support
Starting in R2023a,
resubLoss fully supports GPU arrays.