Accelerated Riemannian Optimization: Handling Constraints with a Prox to Bound Geometric Penalties

November 26, 2022 Β· Declared Dead Β· πŸ› Annual Conference Computational Learning Theory

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors David MartΓ­nez-Rubio, Sebastian Pokutta arXiv ID 2211.14645 Category math.OC: Optimization & Control Cross-listed cs.LG Citations 13 Venue Annual Conference Computational Learning Theory Last Checked 5 months ago
Abstract
We propose a globally-accelerated, first-order method for the optimization of smooth and (strongly or not) geodesically-convex functions in a wide class of Hadamard manifolds. We achieve the same convergence rates as Nesterov's accelerated gradient descent, up to a multiplicative geometric penalty and log factors. Crucially, we can enforce our method to stay within a compact set we define. Prior fully accelerated works \emph{resort to assuming} that the iterates of their algorithms stay in some pre-specified compact set, except for two previous methods of limited applicability. For our manifolds, this solves the open question in [KY22] about obtaining global general acceleration without iterates assumptively staying in the feasible set. In our solution, we design an accelerated Riemannian inexact proximal point algorithm, which is a result that was unknown even with exact access to the proximal operator, and is of independent interest. For smooth functions, we show we can implement the prox step inexactly with first-order methods in Riemannian balls of certain diameter that is enough for global accelerated optimization.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Optimization & Control

Died the same way β€” πŸ‘» Ghosted