Research map / Bandits and online learning / Online convex optimization and games
Mixability made efficient: Fast online multiclass logistic regression
Rémi Jézéquel, Pierre Gaillard, Alessandro Rudi
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 GAF instead of ONS | Online Newton Step · vehicle, segment (LIBSVM) with few samples | averaged online loss | Improved |
| use GAF instead of ONS with many samples | Online Newton Step · vehicle, shuttle, segment | averaged online loss | No clear effect |
| use GAF instead of OGD | Online Gradient Descent · vehicle, shuttle, segment | averaged online loss | No clear effect |
| use Monte Carlo approximation with m=100 samples | GAF · experiments | approximation accuracy: m=100 | No clear effect |
| use GAF instead of ONS regret bound | Online Newton Step · multiclass logistic regression, regret | regret bound: dKe^B log(n) -> dK(B^2 + B log(n)) | Improved |
Closest papers by meaning
- Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability (ICML 2025 · similarity 0.86)
- Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes (ICML 2025 · similarity 0.85)
- Online Linear Regression in Dynamic Environments via Discounting (ICML 2024 · similarity 0.84)
- Oracle Efficient Algorithms for Groupwise Regret (ICLR 2024 · similarity 0.84)
- Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression (NeurIPS 2025 · similarity 0.84)
- MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures (ICLR 2025 · similarity 0.83)
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.
