Research map / Architectures and efficiency / RNNs and normalization
Learning To Stop While Learning To Predict
Xinshi Chen, Hanjun Dai, Yu Li, Xin Gao, Le Song
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 an input-specific stopping policy to LISTA | LISTA · Sparse recovery | NMSE (dB): -17.53 -> -22.41 (mixed SNR) | Improved |
| add task-specific stopping of adaptation steps | MAML · Task-imbalanced Omniglot, 20-way 1-5 shot | accuracy: 97.96 ± 0.3% -> 98.45 ± 0.2% | Improved |
| add task-specific stopping of adaptation steps | MAML · Task-imbalanced MiniImagenet, 5-way 1-10 shot | accuracy: 57.20 ± 1.1% -> 60.67 ± 1.0% | Improved |
| add task-specific stopping of adaptation steps | MAML · Vanilla few-shot meta learning, Omniglot and MiniImagenet | accuracy: Omniglot 5-way 1-shot: 98.7 ± 0.4% -> 99.62 ± 0.22%; MiniImagenet 5-way 5-shot: 63.11 ± 0.92% -> 63.41 ± 0.80% | Mixed |
| add an input-specific stopping policy to DnCNN | DnCNN · BSD68, noise σ=35, 45, and 55 | PSNR: 27.60 -> 27.61 (σ=35); 26.56 -> 26.59 (σ=45); 25.71 -> 25.79 (σ=55) | Improved |
| add an input-specific stopping policy to DnCNN | DnCNN · BSD68, unseen noise σ=65 and σ=75 | PSNR: 22.19 -> 23.56 (σ=65); 17.90 -> 18.62 (σ=75) | Improved |
| use oracle stopping after Stage I training | VGG16 · Tiny-ImageNet | accuracy: 58.60% -> 83.26% | Improved |
| replace oracle stopping with the learned sequential policy | VGG16 · Tiny-ImageNet | accuracy | Hurt |
| replace two-stage oracle training with joint AEVB optimization (ablation) | LISTA-stop · Sparse recovery, mixed SNR | NMSE (dB): -22.41 -> -21.92 | Hurt |
| add optional joint fine-tuning after Stage I + II (ablation) | LISTA-stop · Sparse recovery, mixed SNR | NMSE (dB): -22.41 -> -22.78 | Improved |
| use forward KL rather than reverse KL for policy imitation (ablation) | Stopping policy · Experiments across tasks | prediction performance | Improved |
Closest papers by meaning
- Transfer NAS with Meta-learned Bayesian Surrogates (ICLR 2023 · similarity 0.85)
- Variational Inference for Infinitely Deep Neural Networks (ICML 2022 · similarity 0.85)
- Variational Learning Finds Flatter Solutions at the Edge of Stability (NeurIPS 2025 · similarity 0.84)
- PETRA: Parallel End-to-end Training with Reversible Architectures (ICLR 2025 · similarity 0.84)
- Learning to Stop: Deep Learning for Mean Field Optimal Stopping (ICML 2025 · similarity 0.84)
- Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image Segmentation (AAAI 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.
