Worst-case performance conjecture for gradient descent on linear-operator compositions
Let be a -strongly convex and -smooth function, and let belong to the class of linear operators with singular values in . Write for the corresponding class of functions , and let denote the analogous class with symmetric . For the worst-case performance of the gradient method on a class , measured by the criterion under , the conjecture asserts: Worst-case performance conjecture. For all and ,
Here is the expression given in the cited prior conjecture. This conjecture says that the symmetry of the linear operator does not affect the worst-case performance of gradient descent, extending the previously studied zero-minimal-singular-value case; the supplied text does not establish its resolution.
References
- Nizar Bousselmi, Zhicheng Deng, Jie Lu, Francois Glineur and Julien M. Hendrickx, “On the Convex Interpolation for Linear Operators”, arXiv:2511.16360 (2025).
Progress summary
Nothing recorded yet. Refresh searches the literature and the public web for attempts on this problem, and writes the first summary here.
Solutions 0
No solutions have been posted yet.