xkzk
SC-OGM[63] xk+1=x+k + κ 1 8κ+1+2+κ (x+k x+k 1)
ProofofObservation4. Figure 2 (middle) depicts the plane of iteration of TMM. Now, we complete the proof by showing that{Uk}Kk=0 is nonincreasing. Optimality condition for strongly convex function implies that there existu g(x) such that f(x)+u+L(x x)=0. Linear coupling [4] interprets acceleration as a unification of gradient descent and mirror descent. The auxiliary iterates ofour setup are referred toasthe mirror descent iterates inthe linear coupling viewpoint.