AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Finding Local Minima Efficiently in Decentralized Optimization

Wenhan Xian, Heng Huang

NeurIPS 2023 · Optimization › Nonconvex and smooth optimization · approach: Nonconvex minimax and constrained 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
use PEDESTAL instead of first-order decentralized baselines (D-PSGD, GTDSGD, D-GET, D-SPIDER-SFO, GTHSGD)decentralized matrix sensing · Matrix sensing d=50/100, ring/toroidal/exponential, random dataloss reaching global minimumImproved
use PEDESTAL instead of baselinesdecentralized matrix sensing · Matrix sensing smallest Hessian eigenvalue, d = 50, ring (random)smallest Hessian eigenvalue: -0.0329 -> −1.78e−5Improved
use PEDESTAL instead of baselinesdecentralized matrix sensing · Matrix sensing smallest Hessian eigenvalue, d = 100, exponential (Dirichlet)smallest Hessian eigenvalue: -0.0186 -> −3.63e−6Improved
use PEDESTAL instead of baselinesdecentralized matrix factorization · MovieLens-100k, ring/toroidal/exponential, random and Dirichletloss function valueImproved
variance-reduced methods (D-GET, D-SPIDER-SFO) versus SGD-based D-PSGD and GTDSGDbaselines · MovieLens-100k matrix factorizationescaping saddle point / lossHurt
reduced gradient noise from variance reductiondecentralized baselines · Matrix factorizationsaddle escape abilityHurt
change data distribution from random to Dirichlet Dir20(0.3)PEDESTAL · Matrix sensing, three topologiessaddle escapeNo clear effect
vary network topology (ring, toroidal, exponential graph)PEDESTAL · Matrix sensing d=50, d=100smallest Hessian eigenvalue: −1.78e−5 / −4.18e−5 / −1.09e−6No clear effect
increase dimension from d=50 to d=100all methods · Matrix sensingsmallest Hessian eigenvalue of baselines: -0.0332 -> -0.0184Mixed

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