AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss

Stephen Mussmann, Percy Liang

NeurIPS 2018 · Optimization › Implicit bias and generalization · approach: SGD noise and flat minima · 8 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
Select labels by uncertainty sampling instead of random samplingLogistic regression · Synthetic mixture of four Gaussianszero-one lossMixed
Use different random seed sets to initialize uncertainty samplingLogistic regression · Synthetic mixture of four Gaussianszero-one loss: just over 10%; just over 20%; just over 30%; just over 40%Mixed
Increase the seed set sizeUncertainty sampling · 25 OpenML datasetsvariance of asymptotic zero-one lossImproved
Use uncertainty sampling rather than training on the full datasetLogistic regression · 25 OpenML datasetszero-one lossMixed

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