AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

MADMM: A Generic Algorithm for Non-smooth Optimization on Manifolds

Artiom Kovnatsky, Klaus Glashoff, Michael M. Bronstein

ECCV 2016 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 125 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 MADMM instead of subgradient descent for robust Euclidean embeddingREE (L1 MDS) · REE, US cities n=500iterations to converge: 500 -> 50Improved
use MADMM instead of SDP for robust Euclidean embeddingREE (L1 MDS) · REE scalability, random datascalability with problem size: SDP did not scale beyond n = 100Improved
use robust L1 embedding solved by MADMM instead of classical MDSEuclidean embedding with outlier distances · US cities n=500, doubled distancesembedding quality (qualitative)Improved
vary X-step solver (trust regions vs conjugate gradients) and number of X-step iterations (ablation)MADMM · Compressed modes, n=500, k=10convergence behaviorNo clear effect
change random initialization (ablation)MADMM · Compressed modes, n=500, k=10convergenceNo clear effect
use MADMM instead of splitting methods of Lai-Osher and Neumann et al.compressed modes · Human mesh, n=8Kconvergence speedImproved
use MADMM with L2,1 norm instead of least-squares solutionfunctional correspondence · TOSCA, L=6 shapes, 16% outlierscorrespondence accuracyImproved
use MADMM instead of smoothing the L2,1 normfunctional correspondence · TOSCA, L=2 shapesconvergenceImproved
increase subgradient initial step size c (ablation)subgradient REE solver · US cities n=500convergenceMixed

Later papers that compared with this method

1 later accepted paper reports MADMM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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