AI Paper Atlas

Research map / Optimization / Optimizers

Black-Box Reductions for Zeroth-Order Gradient Algorithms to Achieve Lower Query Complexity

Bin Gu, Xiyuan Wei, Shangqian Gao, Ziran Xiong, Cheng Deng, Heng Huang

JMLR 2021 · Optimization › Optimizers · approach: Zeroth-order training 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
apply AdaptRdct-NC stagewise reduction to ZO-SVRGZO-SVRG · Black-box adversarial attack (Cifar-10, Fmnist, Mnist)attack loss vs function queriesImproved
apply AdaptRdct-C reduction to ZO-SVRG and ZO-SAGAZO-SVRG, ZO-SAGA · Convex logistic regression (German, Ijcnn1, Mushrooms)suboptimality vs function queriesImproved
apply AdaptRdct-NC reduction to ZO-SVRG and ZO-SAGAZO-SVRG, ZO-SAGA · Non-convex logistic regression (German, Ijcnn1, Mushrooms)suboptimality vs function queriesImproved

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