Research map / Learning theory and algorithms / Prediction and decision losses
Minimax Risk Classifiers with 0-1 Loss
Santiago Mazuelas, Mauricio Romero, Peter Grunwald
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 |
|---|---|---|---|
| exploit the subgradient structure (efficient implementation) in the accelerated subgradient method | MRC learning with ASM · MRC optimization running time | running time per iteration: more than 90% reduction in running time per iteration | Improved |
| use the efficient implementation with ASM instead of BSM | MRC learning · Four UCI datasets, optimization error vs time | sparsity coefficient: 10^{-1} -> 10^{-3} | Improved |
| add restarts every 10,000 iterations to E-ASM | E-ASM · Four UCI datasets, optimization error vs time | overall running time: sparsity 10^{-3} -> 10^{-2}, but significantly fewer iterations | Improved |
| solve MRC on a random reduced subset of s instances instead of all instances | MRC error and bounds · Adult and Pulsar, 500 training samples | error probability and bounds | No clear effect |
| vary lambda_0 in the confidence vector (ablation) | MRC · Adult and Pulsar, 1,000 training samples | error probability | No clear effect |
Closest papers by meaning
- Minimax Classification with 0-1 Loss and Performance Guarantees (NeurIPS 2020 · similarity 0.97)
- A Minimax Approach to Supervised Learning (NeurIPS 2016 · similarity 0.87)
- On the Error Resistance of Hinge-Loss Minimization (NeurIPS 2020 · similarity 0.85)
- Robust Minimax Boosting with Performance Guarantees (NeurIPS 2025 · similarity 0.85)
- The optimality of kernel classifiers in Sobolev space (ICLR 2024 · similarity 0.84)
- Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals (NeurIPS 2026 · similarity 0.84)
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.
