Research map / Bandits and online learning / Online convex optimization and games
The Forget-me-not Process
Kieran Milan, Joel Veness, James Kirkpatrick, Michael Bowling, Anna Koop, Demis Hassabis
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 |
|---|---|---|---|
| add FMN on top of PTW + KT | KT base model · Mysterious Bag of Coins | average cumulative regret: 157.19 -> 148.43 | Improved |
| add PTW to KT | KT base model · Mysterious Bag of Coins | average cumulative regret: 783.86 -> 157.19 | Improved |
| add FMN to KT (vs base) | KT base model · Mysterious Bag of Coins | average cumulative regret: 783.86 -> 148.43 | Improved |
| use FMN without complexity-reducing techniques (FMN*) (ablation) | FMN + KT · Mysterious Bag of Coins | average cumulative regret: 148.43 -> 147.75 | No clear effect |
| add PTW to MADE | MADE base model · A Fistful of Digits | average per digit loss: 94.08 -> 94.08 | No clear effect |
| add FMN to MADE | MADE base model · A Fistful of Digits | average per digit loss: 94.08 -> 86.12 | Improved |
| FMN vs offline oracle with per-digit models | FMN + MADE · A Fistful of Digits | average per digit loss: 86.12 vs 82.81 | Hurt |
Closest papers by meaning
- Online Multitask Learning with Long-Term Memory (NeurIPS 2020 · similarity 0.86)
- Posterior Meta-Replay for Continual Learning (NeurIPS 2021 · similarity 0.86)
- Provable Length Generalization in Sequence Prediction via Spectral Filtering (ICML 2025 · similarity 0.84)
- Predictive Attractor Models (NeurIPS 2024 · similarity 0.84)
- Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization (ICML 2024 · similarity 0.83)
- An Information-Theoretic Analysis of In-Context Learning (ICML 2024 · 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.
