AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity

Pan Zhou, Xiaotong Yuan, Jiashi Feng

NeurIPS 2018 · Optimization › Nonconvex and smooth optimization · approach: Stochastic variance reduction · 13 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 without-replacement sampling instead of with-replacement sampling in HSGD (ablation)HSGD · letter, softmax regression, single passobjective valueImproved
HSGD with exponentially growing mini-batch vs SGD, SVRG, SAGA, AVRG, SCGCHSGD (WoRS) · Logistic and softmax regression, single epoch, 8 datasetsobjective distance log(f - f*)Improved
HSGD vs variance-reduced baselines on ill-conditioned softmax regression (lambda=0.001), multi-epochHSGD (WoRS) · protein, satimage, sensorless, letterobjective distance log(f - f*)Improved
Use HSGD-exp (exponential batch growth) for training a 3-layer neural networkHSGD · ijcnn1, covtype, sensorless feedforward NNtraining lossImproved
Linearly instead of exponentially increasing mini-batch size in HSGD (ablation)HSGD on neural networks · ijcnn1, covtypesolution accuracyMixed

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