AI Paper Atlas

Research map / Optimization / Distributed and compressed

Delayed Algorithms for Distributed Stochastic Weakly Convex Optimization

Wenzhi Gao, Qi Deng

NeurIPS 2023 · Optimization › Distributed and compressed · approach: Decentralized optimization algorithms · 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 delayed prox-linear (DSPL) instead of delayed subgradient (DSGD)delayed stochastic method · Robust phase retrieval, async MPIfunction value gap / distance to optimum: 10−2 -> 10−6Improved
Increase number of workersDSGD and DSPL · Robust phase retrieval, async MPIwall-clock time for 400 epochsImproved
Use DSPL instead of DSGDdelayed method · Robust phase retrieval, async MPIwall-clock timeHurt
Increase number of workers (few workers)DSGD and DSPL · Robust phase retrieval, async MPIconvergenceNo clear effect
Use DSPL instead of DSGD under simulated geometric/Poisson delaydelayed method · Robust phase retrieval, simulated delayrange of stepsize parameter alpha ensuring convergenceImproved
Increase simulated delayDSGD and DSPL · Robust phase retrieval, simulated delayiterations to convergeHurt
Add safeguarding step to DSGD (ablation)DSGD · Adversarial delay, zipcode and syntheticfunction valueImproved
Add safeguarding step to DSPL (ablation)DSPL · Adversarial delayfunction valueImproved

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