‖y − x‖2, ∀x, y ∈ Rd. 2. Related Methods asdfGradient Descent Update: xk+1 = xk − h∇f(xk)

Many problems in data science (e.g. machine learning, optimization and statistics) can be cast as loss minimization problems of the form min x∈Rd f(x), where f(x) = 1 n n∑ i=1 fi(x). (P) We assume that each individual function fi: Rd → R is convex and has Lipschitz continuous partial gradients with constants {Lij}j. That is, ‖∇jfi(x)−∇jfi(y) ‖ ≤ Lij‖x − y‖, ∀x, y ∈ Rd. Further we assume that f: Rd → R is µ-strongly convex: f(y) ≥ f(x) + 〈∇f(x), y − x〉+