AI Paper Atlas

Research map / Optimization / Optimizers

Adaptive Gradient Descent without Descent

Yura Malitsky, Konstantin Mishchenko

ICML 2020 · Optimization › Optimizers · approach: Second-order and structured preconditioning · 16 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 adaptive stepsizes estimated from gradients instead of SGD's tuned scheduleCIFAR10 ResNet-18 training · CIFAR10test accuracyImproved
Use adaptive stepsizes estimated from gradients instead of SGD's tuned scheduleCIFAR10 ResNet-18 training · CIFAR10early-stage training speedHurt
Use adaptive stepsizes estimated from gradients instead of SGD's tuned scheduleCIFAR10 ResNet-18 training · CIFAR10training stabilityHurt
Change the logistic-regression datasetBarzilai-Borwein stepsize · Logistic regression, mushrooms/covtypeconvergenceMixed
Use Armijo line search rather than AdGDLogistic regression · Logistic regression, mushrooms/covtype/w8aiteration cost: approximately 2 times more expensive than AdGDHurt
Use Nesterov GD with line search rather than AdGDLogistic regression · Logistic regression, mushrooms/covtype/w8aiteration cost: 4 times more expensiveHurt
Use the same stochastic sample to estimate the stepsize and compute the updateAdaptive SGD for overparameterized models · Neural network experimentsperformanceImproved

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