Research map / Optimization / Optimizers
Continuous-Time Meta-Learning with Forward Mode Differentiation
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 COMLN instead of MAML | Conv-4 · miniImageNet 5-way 1-shot | accuracy: 48.70 ± 1.84 -> 53.01 ± 0.62 | Helped |
| Use COMLN instead of MAML | Conv-4 · miniImageNet 5-way 5-shot | accuracy: 63.11 ± 0.92 -> 70.54 ± 0.54 | Helped |
| Use COMLN instead of MAML | ResNet-12 · tieredImageNet 5-way 1-shot | accuracy: 55.37 ± 0.74 -> 62.93 ± 0.71 | Helped |
| Use COMLN instead of MAML | ResNet-12 · tieredImageNet 5-way 5-shot | accuracy: 72.93 ± 0.60 -> 81.13 ± 0.53 | Helped |
| Use COMLN instead of MetaOptNet-SVM | ResNet-12 · miniImageNet 5-way 1-shot | accuracy: 62.64 ± 0.61 -> 59.26 ± 0.65 | Hurt |
| Use COMLN instead of MetaOptNet-SVM | ResNet-12 · tieredImageNet 5-way 5-shot | accuracy: 81.56 ± 0.53 -> 81.13 ± 0.53 | Hurt |
Closest papers by meaning
- Large-Scale Meta-Learning with Continual Trajectory Shifting (ICML 2021 · similarity 0.90)
- Submodular Meta-Learning (NeurIPS 2020 · similarity 0.89)
- On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation (NeurIPS 2022 · similarity 0.89)
- Scalable Bayesian Meta-Learning through Generalized Implicit Gradients (AAAI 2023 · similarity 0.89)
- Memory-Reduced Meta-Learning with Guaranteed Convergence (AAAI 2025 · similarity 0.88)
- MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning (AAAI 2024 · similarity 0.88)
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.