REVIEW 1 cited by
No-go Theorem for Acceleration in the Hyperbolic Plane
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In recent years there has been significant effort to adapt the key tools and ideas in convex optimization to the Riemannian setting. One key challenge has remained: Is there a Nesterov-like accelerated gradient method for geodesically convex functions on a Riemannian manifold? Recent work has given partial answers and the hope was that this ought to be possible. Here we dash these hopes. We prove that in a noisy setting, there is no analogue of accelerated gradient descent for geodesically convex functions on the hyperbolic plane. Our results apply even when the noise is exponentially small. The key intuition behind our proof is short and simple: In negatively curved spaces, the volume of a ball grows so fast that information about the past gradients is not useful in the future.
Forward citations
Cited by 1 Pith paper
-
Horospherically Convex Optimization on Hadamard Manifolds Part I: Analysis and Algorithms
A new class of functions, horospherically convex functions, admits gradient, subgradient, and accelerated methods with curvature-independent Euclidean rates on Hadamard manifolds.
Discussion (0). Sign in to comment.