AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Gradient-Normalized Smoothness for Optimization with Approximate Hessians

Andrei Semenov, Martin Jaggi, Nikita Doikov

ICLR 2026 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use approximate Weighted Gauss-Newton Hessian instead of exact Hessian (ablation)Gradient-regularized Newton · LogSumExp (libsvm datasets)convergence speedNo clear effect
use second-order method instead of Gradient MethodGradient-regularized Newton with inexact Hessian · LogSumExpconvergence speedImproved
use function-value adaptive search instead of gradient-norm search (ablation)Gradient-regularized Newton · LogSumExpstep-size gamma_kImproved
add Gauss-Newton preconditioner to Gradient Method (ablation)Gradient Method · Nonlinear Equations (linear operator, p=2..5)convergence speedImproved
use Fisher-type rank-one Hessian approximation instead of exact Newton (ablation)Gradient-regularized Newton · Nonlinear Equations (MNIST, synthetic)wall-clock timeImproved
use inexact Hessian instead of exact Hessian (ablation)Gradient-regularized Newton · Rosenbrock Nonlinear Equationsrobustness to starting pointImproved
use Gradient Method with our adaptive search at large p (ablation)Gradient Method · Nonlinear Equations (linear operator)convergence speedHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy