Research map / Time series / Causal and generative time series
Continuous Meta-Learning without Tasks
James Harrison, Apoorva Sharma, Chelsea Finn, Marco Pavone
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 |
|---|---|---|---|
| Use MOCA with ALPaCA instead of fixed sliding-window baselines | ALPaCA · Sinusoid regression | NLL | Improved |
| Use MOCA with ALPaCA instead of fixed sliding-window baselines | ALPaCA · Switching wheel bandit | regret | Mixed |
| Use MOCA with an LSTM meta-learner instead of condition-on-everything and other baselines | LSTM meta-learner · NBA player movement | NLL | Improved |
| Use MOCA with PCOC instead of baselines | PCOC · Rainbow MNIST | accuracy | Improved |
| Use MOCA with PCOC instead of baselines | PCOC · miniImageNet | accuracy | Improved |
| Add the current encoded input to the LSTM decoder alongside the hidden state (ablation) | LSTM meta-learner · Regression experiments | performance | Improved |
Closest papers by meaning
- Advances and Challenges in Meta-Learning: A Technical Review (TPAMI 2024 · similarity 0.89)
- When Meta-Learning Meets Online and Continual Learning: A Survey (TPAMI 2024 · similarity 0.89)
- Continuous-Time Meta-Learning with Forward Mode Differentiation (ICLR 2022 · similarity 0.88)
- Reconciling meta-learning and continual learning with online mixtures of tasks (NeurIPS 2019 · similarity 0.88)
- Online Meta-Learning (ICML 2019 · similarity 0.87)
- Submodular Meta-Learning (NeurIPS 2020 · 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.
