For twice-differentiable smooth strongly convex functions, the C2M method converges globally with worst-case rate rho_C2M < 1 - sqrt(2/kappa), strictly faster than the Triple Momentum method's 1 - 1/sqrt(kappa) rate.
Robust and structure exploiting optimisation algorithms: An integral quadratic constraint approach,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
The Fastest Known First-Order Method for Minimizing Twice Continuously Differentiable Smooth Strongly Convex Functions
For twice-differentiable smooth strongly convex functions, the C2M method converges globally with worst-case rate rho_C2M < 1 - sqrt(2/kappa), strictly faster than the Triple Momentum method's 1 - 1/sqrt(kappa) rate.