bias-variance tradeoff

$(E[\hat{f}(x)]-f(x){)}^2+E[\hat{f}(x)-E[\hat{f}(x)]{]}^2+{\sigma }_e^2.$ where

• $\hat{f}$ is the model
• $E[\hat{f}(x)]-f(x)$ is the bias
• $E[\hat{f}(x)-E[\hat{f}(x)]{]}^2$ is the variance
• ${\sigma }_e^2$ is the irreducible error

Related to model complexity