Research map / Learning theory and algorithms / Prediction and decision losses
Logarithmic Time One-Against-Some
Hal Daumé III, Nikos Karampatziakis, John Langford, Paul Mineiro
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 |
|---|---|---|---|
| Use Recall Tree instead of OAA | Multiclass classification · ALOI | test error (default): 12.2% -> 11.4% | Improved |
| Use Recall Tree instead of OAA | Multiclass classification · ImageNet | test error (default): 84.7% -> 91.1% | Hurt |
| Use Recall Tree instead of OAA | Multiclass classification · LTCB | test error (default): 78.7% -> 78.0% | Improved |
| Use Recall Tree instead of OAA | Multiclass classification · ODP | test error (default): 91.2% -> 96.2% | Hurt |
| Use Recall Tree instead of LOMTree | Multiclass classification · ALOI | test error (default): 21.4% -> 11.4% | Improved |
| Use Recall Tree instead of LOMTree | Multiclass classification · ImageNet | test error (default): 96.7% -> 91.1% | Improved |
| Use Recall Tree instead of LOMTree | Multiclass classification · LTCB | test error (default): 78.4% -> 78.0% | Improved |
| Use Recall Tree instead of LOMTree | Multiclass classification · ODP | test error (default): 95.4% -> 96.2% | Hurt |
| Add path features to the Recall Tree predictors (ablation) | Recall Tree on ALOI · ALOI | test error | Improved |
| Use path features at candidate set size 2 (ablation) | Recall Tree on ALOI · ALOI | test error | No clear effect |
| Use multiple predictors per leaf (ablation) | Recall Tree on ALOI · ALOI | test error | Improved |
| Increase the candidate set size (ablation) | Recall Tree on ALOI · ALOI | test error | Improved |
Closest papers by meaning
- Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View (NeurIPS 2020 · similarity 0.83)
- Unified Binary and Multiclass Margin-Based Classification (JMLR 2024 · similarity 0.83)
- A Trichotomy for List Transductive Online Learning (ICML 2025 · similarity 0.81)
- Don’t Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget (ICML 2024 · similarity 0.81)
- Scaled Decoupled Distillation (CVPR 2024 · similarity 0.81)
- Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment (ICLR 2025 · similarity 0.81)
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.
