113 citations · 128 across the 10 of their papers we have counts for
3 papers · 1 filter
Gradient-Normalized Smoothness for Optimization with Approximate Hessians
Andrei Semenov, Martin Jaggi, Nikita Doikov
In this work, we develop new optimization algorithms that use approximate second-order information combined with the gradient regularization technique to achieve fast global conver…
Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions
Nikita Doikov, Sebastian U. Stich, Martin Jaggi
The performance of optimization methods is often tied to the spectrum of the objective Hessian. Yet, conventional assumptions, such as smoothness, do often not enable us to make fi…
Screening Rules for Convex Problems
Anant Raj, Jakob Olbrich, Bernd Gärtner +2
We propose a new framework for deriving screening rules for convex optimization problems. Our approach covers a large class of constrained and penalized optimization formulations,…