Theorem 4.2 — with $n_k \ge a^k$, dynamic batch steepest descent satisfies $E[J(w_k)-J(w^*)] \le C\rho^k$

Initializing...

Theorem 4.2 — with $n_k \ge a^k$, dynamic batch steepest descent satisfies $E[J(w_k)-J(w^*)] \le C\rho^k$ · Prove2Me