Research map / Bandits and online learning / Multi-armed bandits
Automated Curriculum Learning for Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GVCG-guided adaptive task sampling instead of uniform sampling | LSTM with variational inference · Repeat copy | target-task learning speed | Helped |
| Use PG-guided adaptive task sampling instead of uniform sampling | LSTM with maximum likelihood · bAbI | learning speed and tasks completed | Helped |
| Use SPG-guided adaptive task sampling instead of uniform sampling | LSTM with maximum likelihood · bAbI | learning speed and tasks completed | Helped |
| Use PG-guided adaptive task sampling instead of uniform sampling | LSTM with maximum likelihood · Repeat copy | target-task learning speed | Helped |
| Use SPG-guided adaptive task sampling instead of uniform sampling | LSTM with maximum likelihood · Repeat copy | target-task learning speed | Helped |
| Use TPG-guided adaptive task sampling instead of uniform sampling | LSTM with maximum likelihood · Repeat copy | target-task learning speed | Helped |
| Use GVCG-guided adaptive task sampling instead of uniform sampling | LSTM with variational inference · bAbI | learning speed | Mixed |
| Use VCG-guided adaptive task sampling instead of uniform sampling | LSTM with variational inference · bAbI | learning progress | Hurt |
| Use L2G-guided adaptive task sampling instead of uniform sampling | LSTM with maximum likelihood · Repeat copy | target-task learning speed | Hurt |
| Use GPG-guided adaptive task sampling instead of uniform sampling | LSTM with maximum likelihood · Repeat copy | target-task learning speed | Hurt |
| Use GL2G-guided adaptive task sampling instead of uniform sampling | LSTM with maximum likelihood · Repeat copy | target-task learning speed | Hurt |
| Train directly on the target task rather than using a curriculum | LSTM · Repeat copy | target-task learning | Hurt |
Closest papers by meaning
- Bandit Guided Submodular Curriculum for Adaptive Subset Selection (NeurIPS 2025 · similarity 0.86)
- CurBench: Curriculum Learning Benchmark (ICML 2024 · similarity 0.85)
- Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks (ICML 2024 · similarity 0.84)
- Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers (ICML 2024 · similarity 0.84)
- Toward Student-oriented Teacher Network Training for Knowledge Distillation (ICLR 2024 · similarity 0.84)
- Progressive distillation induces an implicit curriculum (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.