
The paper establishes the linear convergence of NAG and FISTA for strongly convex functions without requiring any prior knowledge of the modulus of strong convexity.


coremsg

linear-convergence-of-forward-backward-accelerated-algorithms-for-strongly-convex-functions-without-knowledge-of-the-modulus-of-strong-convexity


Linear Convergence of Forward-Backward Accelerated Algorithms for Strongly Convex Functions Without Knowledge of the Modulus of Strong Convexity
