1.Empirical risk minimization is prone to overfitting.
2.Many useful loss fucntions have no derivatives.

University of Michigan - Ann Arbor

The training process based on minimizing this average training error is known
as empirical risk minimization.

Empirical Risk Minimization

Goodfellow, I., Bengio, Y., & Courville, A. (2016). $\mathit{Deep \ Learning.}$ MIT Press. Retrieved from [www.deeplearningbook.org](https://www.deeplearningbook.org) 

Deep Learning

Disadvantage of ERM(Empirical risk minimization)

When the model is probability distribution and the loss function is log-likelihood loss function, ERM is actually a maximum likelihood estimation.

Basic case of ERM

Structural risk minimization (SRM) is a machine learning principle that addresses empirical risk minimization's susceptibility to overfitting by balancing the empirical risk against model complexity.

Learn Before

Related