# Is “model selection” the same as traning?

A terminology problem. In machine learning we have the following problem:

Choosing the optimal model (or training): $$f^* = \arg\min_{f \in \mathcal{F}} \sum_i l(x_i,y_i)$$

Is the term "model selection" always "exactly" referring to this? Or something else?

• No, because model selection can have additional cost constraints (such as reducing complexity of $f$). – pat Oct 28 '13 at 17:15
• Could you elaborate? Or could you give me some pointers? – Daniel Oct 28 '13 at 17:18
• No. In many approaches, for example SVM, training means solving a given optimization problem which itself is parametrized. Model selection means finding the right parameters. – Marc Claesen Oct 28 '13 at 18:05