The orthogonal Procrustes problem satisfies weak-quasi-strong-convexity, yielding linear convergence of Riemannian gradient descent for invertible matrices and O(1/t) function-value convergence for singular ones.
A Note on Nesterov's Accelerated Method in Nonconvex Optimization: a Weak Estimate Sequence Approach
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We present a variant of accelerated gradient descent algorithms, adapted from Nesterov's optimal first-order methods, for weakly-quasi-convex and weakly-quasi-strongly-convex functions. We show that by tweaking the so-called estimate sequence method, the derived algorithm achieves optimal convergence rate for weakly-quasi-convex and weakly-quasi-strongly-convex in terms of oracle complexity. In particular, for a weakly-quasi-convex function with Lipschitz continuous gradient, we require $O(\frac{1}{\sqrt{\varepsilon}})$ iterations to acquire an $\varepsilon$-solution; for weakly-quasi-strongly-convex functions, the iteration complexity is $O\left( \ln\left(\frac{1}{\varepsilon}\right) \right)$. Furthermore, we discuss the implications of these algorithms for linear quadratic optimal control problem.
citation-role summary
citation-polarity summary
fields
math.NA 1years
2024 1verdicts
ACCEPT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A geodesic convexity-like structure for the polar decomposition of a square matrix
The orthogonal Procrustes problem satisfies weak-quasi-strong-convexity, yielding linear convergence of Riemannian gradient descent for invertible matrices and O(1/t) function-value convergence for singular ones.