atlas

Research map / Optimization / Nonconvex and smooth optimization

Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines

ICML 2018 · Optimization › Nonconvex and smooth optimization · approach: Stochastic convex optimization complexity · 18 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
Add SVRG variance reduction and mini-batch to asynchronous stochastic zeroth-order gradients (AsySZO+ vs AsySZO)asynchronous stochastic zeroth-order optimization · ensemble learning (KDD-Cup 2011 ensemble objective)convergence rate of gradient norm: O(1/sqrt(T)) to O(1/(bT))Helped
Mini-batch size 100 vs 1 in AsySZO+ (ablation)AsySZO+ · ensemble learning (KDD-Cup 2011)objective and gradient norm vs epochHelped
Asynchronous parallel execution with no locks (AsySZO+ scaled from 1 to 16 cores)AsySZO+ · ensemble learning (KDD-Cup 2011)speedupHelped
Sequential SZO+ (SVRG + mini-batch) vs SZO on one coreSZO+ · ensemble learning (KDD-Cup 2011), 1 coreconvergence of objective and gradient normHelped

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