Research map / Optimization / Implicit bias and generalization
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss
Stephen Mussmann, Percy Liang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Select labels by uncertainty sampling instead of random sampling | Logistic regression · Synthetic mixture of four Gaussians | zero-one loss | Mixed |
| Use different random seed sets to initialize uncertainty sampling | Logistic regression · Synthetic mixture of four Gaussians | zero-one loss: just over 10%; just over 20%; just over 30%; just over 40% | Mixed |
| Increase the seed set size | Uncertainty sampling · 25 OpenML datasets | variance of asymptotic zero-one loss | Improved |
| Use uncertainty sampling rather than training on the full dataset | Logistic regression · 25 OpenML datasets | zero-one loss | Mixed |
Closest papers by meaning
- Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent (NeurIPS 2023 · similarity 0.90)
- On the Convergence of Loss and Uncertainty-based Active Learning Algorithms (NeurIPS 2024 · similarity 0.89)
- Stochastic Reweighted Gradient Descent (ICML 2022 · similarity 0.88)
- The Sample Complexity of Gradient Descent in Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.88)
- Convergence of Uncertainty Sampling for Active Learning (ICML 2022 · similarity 0.88)
- Uncertainty for Active Learning on Graphs (ICML 2024 · similarity 0.86)
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.
