AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Exact Optimal Accelerated Complexity for Fixed-Point Iterations

ICML 2022 · Learning theory and algorithms › Optimal transport · approach: Sinkhorn and entropic OT algorithms · 3 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Halpern-type acceleration (OC-Halpern / OS-PPM) with optimal rate in place of Picard/PPMnonexpansive and contractive fixed-point iterations · 2D toy examplefixed-point residual / resolvent residualHelped
Restarting OS-PPM (restarted OC-Halpern) under uniform monotonicity / Hölder-type growthPDHG for total variation CT · CT imagingfixed-point residualHelped
Restarted OC-Halpern accelerationPDHG for earth mover's distance · Earth mover's distancefixed-point residualHelped
Restarted OC-Halpern accelerationPG-EXTRA for decentralized compressed sensing · Decentralized compressed sensingfixed-point residualHelped
Matching lower bound: no deterministic fixed-point method can beat the OC-Halpern rate for 1/gamma-Lipschitz operatorsgeneral deterministic fixed-point iterations · theory (nonexpansive/contractive)squared fixed-point residual rateNo 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