Nov 19, 2019 · We provide a lower bound showing that the O(1/k) convergence rate of the NoLips method (aka Bregman Gradient) is optimal for the class of functions satisfying ...

Apr 21, 2021 · First, we provide a lower bound showing that it is impossible to generically accelerate Bregman gradient methods under the appropriate oracle ...

ABSTRACT: We provide a lower bound showing that the O(1/k) convergence rate of the NoLips method (a.k.a. Bregman Gradient) is optimal for the class of functions ...

Oct 22, 2024 · This technique allows computing worst-case scenarios for NoLips in the context of relatively-smooth minimization. In particular, we used ...

This technique allows computing worst-case scenarios for NoLips in the context of relatively-smooth minimization. In particular, we used numerically generated ...

This study analyzes worst-case convergence guarantees of first-order optimization methods over a function class extending that of smooth and convex functions.

Nov 21, 2019 · We analyze worst-case convergence guarantees of first-order optimization methods over a function class extending that of smooth and convex ...

Apr 21, 2021 · Optimal complexity and certification of Bregman first-order methods. 43 proven to be optimal for L-smooth functions and have found a number ...

In this paper, besides the oracle complexity, we focus also on iteration complexity, and propose a generic approach that, based on optimal first-order methods, ...

Sep 29, 2020 · Accepted for publication in Mathematical Programming. https://doi.org/10.1007/s10107-021-01618-1. Optimal Complexity and Certification of ...