Research map / Continual learning / Online and replay-based
The Ideal Continual Learner: An Agent That Never Forgets
Liangzu Peng, Paris Giampouras, Rene Vidal
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 |
|---|---|---|---|
| define the Ideal Continual Learner that jointly satisfies all task constraints | ICL · theory | forgetting | Improved |
| rehearsal with a stored subset of previous data | ICL / rehearsal · theory | generalization guarantee | Improved |
| increase network width | ICL-dagger / deep continual learning · theory | catastrophic forgetting | Improved |
| view multitask learning as the ICL special case | ICL · theory | continual learning performance | Improved |
| choose representative or diverse samples versus random for rehearsal memory | memory selection · text classification and QA (cited study) | performance | No clear effect |
| domain-incremental learning without architecture change | ICL · theory | forgetting | Mixed |
Closest papers by meaning
- Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective (ICML 2025 · similarity 0.91)
- A Unified and General Framework for Continual Learning (ICLR 2024 · similarity 0.91)
- STAR: Stability-Inducing Weight Perturbation for Continual Learning (ICLR 2025 · similarity 0.90)
- Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization (ICML 2024 · similarity 0.90)
- Optimal Protocols for Continual Learning via Statistical Physics and Control Theory (ICLR 2025 · similarity 0.90)
- Learn more, but bother less: parameter efficient continual learning (NeurIPS 2024 · similarity 0.89)
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.
