AI Paper Atlas

Research map / Optimization / Optimizers

Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity

William de Vazelhes, Hualin Zhang, Huimin Wu, Xiaotong Yuan, Bin Gu

NeurIPS 2022 · 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
use smaller number of random directions q (ablation)SZOHT · toy sparse quadric (d=5000)f(x) descentHurt
use q = 1 or 20 random directions (ablation)SZOHT · toy sparse quadric (d=5000)distance to optimumHurt
SZOHT vs ZSCG, RSPGFSZOHT · sparse asset risk management (port3, port4, port5)f(x) vs queriesImproved
SZOHT vs ZSCG, RSPGF, ZOROSZOHT · few-pixel adversarial attack (MNIST, CIFAR, ImageNet)f(x) vs queriesImproved
proximal RSPGF vs Frank-Wolfe ZSCGRSPGF · sparse portfolio and attack tasksconvergence speedImproved
ZORO assumes sparse gradientsZORO · real-world sparse tasksearly-stage convergenceHurt

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