Houjun Liu


function that returns the input that maximizes the expression.

finding argmax

direct optimization

Typical maximization system. Take derivative, set it to 0, solve, plug in, solve. THis is pretty bad during times are not differentiable.

gradient ascent

We take steps following the direction

\begin{equation} \theta_{1j} = \theta_{0j} + \eta \pdv{LL(\theta_{0})}{\theta_{0j}} \end{equation}

additional information

argmax of log

see argmax of log