- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies the local convergence of NAG under the local PL condition. It provides a sharp local rate for standard NAG that converges at a rate of (1-1/\sqrt{\kappa}).
Critical strengths
PL condition is a fundamental setting to study in optimization. This paper provides new insight for the nesterov accelerated gradient method. It shows that NAG provide acceleration for minimizing local PL objectives, locally.
Critical weaknesses
-
The results are not clearly presented regarding the local region: in theorem 2.2, it only shows that there exists a sufficiently small open neighborhood, but the radius of the neighborhood is not clearly presented. This limits the practical impact of the proposed theory.
-
The exact contrating factort of the local linear rate of NAG cannot be precisely quantified, which introduce additional in the rate. I think this should impact the initial condition or the local condition.
Questions for authors
Please refer to weakness.
Response to W1:
We thank the reviewer for the constructive comments.
Theorem 2.2 establishes the existence of a sufficiently small neighborhood in which the local convergence result holds. Under the general assumptions of C2 smoothness and the local PL condition, such a result is naturally qualitative. In particular, the continuity of the Hessian does not provide an explicit quantitative estimate of its variation. Therefore, the size of the admissible neighborhood depends on the specific objective function and its local properties, and cannot generally be determined explicitly under our assumptions. Obtaining an explicit radius would require additional quantitative regularity assumptions, which are beyond the scope of our current framework.
Our primary objective is to characterize the sharp local asymptotic convergence rate under these mild regularity assumptions, rather than to provide an explicit estimate of the attraction region.
Response to W2:
We emphasize that the optimal spectral radius is precisely characterized in Theorem 2.2 as
ρopt=3L+μ3L+μ−2μ. The additional ε>0 is an arbitrarily small allowance introduced in deriving the uniform geometric convergence estimate. It accounts for the higher-order nonlinear remainder terms arising from the C2 linearization, as well as the passage from the spectral-radius estimate to a uniform bound on the iterates.
We also note that the admissible initial neighborhood and the constant in the convergence estimate may depend on ε. In particular, a smaller ε may require a smaller initial neighborhood to control the higher-order terms. This dependence is already reflected in the statement of Theorem 2.2.
Thus, ρopt remains the precisely characterized optimal spectral radius, while the additional ε provides the required flexibility in establishing the local geometric convergence estimate.
We hope these clarifications address the reviewer's concerns.