Research map / Learning theory and algorithms / Prediction and decision losses
Agnostic Learning with Multiple Objectives
Corinna Cortes, Mehryar Mohri, Javier Gonzalvo, Dmitry Storcheus
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 |
|---|---|---|---|
| Replace uniform mixture weights with ALMO | Logistic regression · MNIST | cross-entropy loss: 0.1412 -> 0.0726 | Improved |
| Replace uniform weights with ALMO | Logistic regression · Adult | hinge loss: 0.967 -> 0.518 | Improved |
| Replace uniform weights with ALMO | Logistic regression · Adult | cross-entropy loss: 0.680 -> 0.501 | Improved |
| Replace uniform weights with ALMO | Logistic regression · Fashion MNIST | hinge loss: 0.633 -> 0.695 | Hurt |
| Replace uniform weights with ALMO (1-norm loss gets low weight) | Logistic regression · MNIST | 1-norm loss: 0.2349 -> 0.6587 | Hurt |
| Replace uniform weights with ALMO | Logistic regression · Adult | AUC: 0.8291 -> 0.8321 | Improved |
| Replace uniform weights with ALMO | Logistic regression · MNIST | AUC: 0.9801 -> 0.9877 | Improved |
| Replace uniform weights with ALMO | DNN · Adult | hinge loss: 0.914 -> 0.389 | Improved |
| Replace uniform weights with ALMO | DNN · Adult | AUC: 0.8092 -> 0.8840 | Improved |
| Replace uniform weights with ALMO | DNN · MNIST | cross-entropy loss: 0.044 -> 0.045 | No clear effect |
| Replace uniform weights with ALMO | DNN · MNIST | hinge loss: 0.631 -> 0.752 | Hurt |
| Replace uniform weights with ALMO | DNN · Fashion MNIST | hinge loss: 0.661 -> 0.547 | Improved |
Closest papers by meaning
- On the sample complexity of semi-supervised multi-objective learning (NeurIPS 2025 · similarity 0.85)
- Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance (NeurIPS 2023 · similarity 0.84)
- Learning Configurations for Data-Driven Multi-Objective Optimization (ICML 2025 · similarity 0.84)
- MEPSI: An MDL-Based Ensemble Pruning Approach with Structural Information (AAAI 2024 · similarity 0.83)
- Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms (ICML 2024 · similarity 0.83)
- Many-Objective Multi-Solution Transport (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.
