AI Paper Atlas

Research map / Optimization / Optimizers

Stochastic Reweighted Gradient Descent

Ayoub El Hanchi, David Stephens, Chris Maddison

ICML 2022 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 3 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 SRG's adaptive importance sampling and gradient-norm table instead of uniform SGD samplingSGD · ijcnn1, w8a, mushrooms, phishingrelative error: about an order of magnitude more accurateImproved
Use SRG instead of SGDSGD · Synthetic linear regressionrelative error: approximately two orders of magnitude more accurateImproved
Use SRG instead of SGDSGD · ijcnn1, w8a, mushrooms, phishing; decreasing step sizesrelative errorImproved
Use SRG instead of SGD with random shufflingSGD with random shuffling · ijcnn1, w8a, mushrooms, phishing; decreasing step sizesrelative errorHurt
Use SRG instead of SVRGSVRG · ijcnn1, w8a, mushrooms, phishing; constant step sizerelative errorMixed
Use SRG rather than uniform samplingSGD · Synthetic linear regressiongradient estimator variance: r ≈ 50Improved
Use SRG's adaptive samplingSGD · Strongly-convex finite-sum optimizationasymptotic error dependence: σ^2 -> σ_*^2Improved

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