Empirical Risk
Jump to navigation
Jump to search
See: Risk, Likelihood.
References
- http://clopinet.com/isabelle/Projects/ETH/Exam_Questions.html
- The empirical risk is the average loss over a finite number of given examples. Empirical risk minimization refers to finding the function f(x) in a family of functions that minimizes the empirical risk. Empirical risk minimization is a form of training/learning. … The risk may be interpreted as an "energy". A likelihood can be defined following the Boltzman distribution P(D|f)= exp -R[f]/T, where T is a "temperature" parameter. With this correspondance, minimizing the risk is equivalent to maximizing the likelihood.