Typically, when one has enough data, the empirical loss concentrates around the expected loss: there exists con $>0,$ such that for any f in H$,|$L$($f$)$ L$($f$)|<=$ con. Show that

in this case, est $<=2$con.

Comments: This means that to get small estimation error, the number of data points should

be large enough so that concentration happens. The number of data points needed to get

concentration con is called sample complexity, which is an important topic in learning

theory and statistics.