Register

Go Classes | DA Course | Machine Learning

289 views

2 Answers

1 1 vote

Yes, the labels

{1,…,K} can be treated as integers and a regression model can be fitted.

 However, this is not recommended 

because regression imposes an artificial ordinal and metric structure on class labels and minimizes squared error, which is inappropriate for categorical outputs. This leads to incorrect loss behavior, poor decision boundaries, and lack of probabilistic interpretation.

 Therefore, classification-specific models are preferred.

Voting & Accepting an answer helps improve the community
← Previous · Go Classes | DA Cour...Next → · Go Classes | DA Cour...
← Previous in category · Go Classes | DA Cour...Next in category → · Go Classes | DA Cour...
Position:
Show:

Related questions

1 1 vote
1 1 answer
507
507 views
GO Classes asked Mar 18, 2025
507 views
GO Classes | DA Course | Machine Learning
Consider linear regression and logistic regression. They both use linear functions.They both can be used to solve regression prob-They both use the logistic activation fu...
1 1 vote
1 1 answer
250
250 views
GO Classes asked Mar 13, 2025
250 views
Go Classes | DA Course | Machine Learning
Consider a simple classification task with features $x_i \in \mathbb{R}^d$ and $k$ classes. Suppose we train a linear classifier to minimize the regularized least squared...
1 1 vote
1 1 answer
250
250 views
GO Classes asked Mar 13, 2025
250 views
GO Classes | DA Course| Machine Learning
Consider just the general shape of the following plots.For each of the following possible interpretations of the quantities being plotted on the $X$ and $Y$ axes, indicat...
1 1 vote
0 0 answers
188
188 views
GO Classes asked Mar 13, 2025
188 views
Go Classes | DA Course | Machine Learning
Consider the following training data: xy132130.5Suppose the data comes from a model $y=c x^\beta$ , for unknown constants $c$ and $\beta$. Use least squares linear regres...