AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Polynomial Preconditioning for Gradient Methods

Nikita Doikov, Anton Rodomanov

ICML 2023 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 0 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
Add symmetric polynomial preconditioner P1 = tr(B)I - B to the Gradient Method (ablation)Gradient Method · Huber loss regression (synthetic, gap between λ1 and λ2)func. residual convergenceImproved
Add symmetric polynomial preconditioner P2 to the Gradient Method (ablation)Gradient Method · Huber loss regression (synthetic, gap between λ1 and λ3)func. residual convergenceImproved
Use symmetric polynomial preconditioner P2 instead of identity in Gradient MethodGradient Method · Logistic regression (mnist and other LIBSVM datasets)iterations / matrix-vector products to reach func. residual: two times fasterImproved
Use symmetric polynomial preconditioner P2 in Fast Gradient Method instead of identityFast Gradient Method · Logistic regression (mnist and other LIBSVM datasets)iterations / matrix-vector products to reach func. residual: about 1.5 times fasterImproved
Use Krylov (adaptive optimal polynomial) preconditioning in Gradient MethodGradient Method · Logistic regression (LIBSVM datasets)iterations to reach func. residualImproved
Use symmetric polynomial preconditioning P1 and P2 in GM and FGM without extra per-iteration arithmetic costGradient Method and Fast Gradient Method · Logistic regression (a9a, phishing, breast-cancer, ionosphere, covtype, mnist)func. residual vs iterationsImproved
Use Krylov preconditioning with higher degree (τ=3 vs lower) and higher cost per iterationGradient Method · Logistic regression (LIBSVM datasets)matrix-vector productsMixed
Use GM with symmetric polynomial preconditioner P2 (order τ=2)Gradient Method · Soft maximum (log-sum-exp) objective, n=100, m=200matrix-vector products and time to residualImproved
Use FGM with symmetric polynomial preconditioner P2Fast Gradient Method · Soft maximum (log-sum-exp) objectivematrix-vector products and time vs BFGSNo clear effect

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