Research map / Continual learning / Online and replay-based
Coreset Selection via Reducible Loss in Continual Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes coreset selection for rehearsal-based continual learning using reducible loss, based on the abstract's bilevel formulation of coreset selection.
Problem
Rehearsal-based continual learning must store a compact memory of past-task samples that preserves performance comparable to full data, to mitigate catastrophic forgetting; coreset selection for this memory is posed as bilevel optimization.
Approach
Uses a reducible loss to guide coreset selection for the rehearsal memory in continual learning, as suggested by the title; the full method details are not available in the provided text.
Closest papers by meaning
- Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective (ICML 2025 · similarity 0.90)
- STAR: Stability-Inducing Weight Perturbation for Continual Learning (ICLR 2025 · similarity 0.88)
- Predicting the Susceptibility of Examples to Catastrophic Forgetting (ICML 2025 · similarity 0.87)
- Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes (NeurIPS 2025 · similarity 0.87)
- Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization (ICML 2024 · similarity 0.87)
- Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning (NeurIPS 2026 · similarity 0.87)
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.