a Brief Review of Statistical Learning Given a loss function f and distribution D,the expected risk of predictor h is R(h)=E(xD[(h(x),y)]. In practice,we can only access to a sample set S={(x1,1),...,(xm,Um)} Thus,the following empirical risk is naturally defined: Rsm=工x.8 77 i=1 Advanced Optimization(Fall 2023) Lecture 5.Online Convex Optimization 4Advanced Optimization (Fall 2023) Lecture 5. Online Convex Optimization 4 A Brief Review of Statistical Learning