Research map / Time series / Long-term forecasting
Tuning the burn-in phase in training recurrent neural networks improves their performance
Julian D. Schiller, Malte Heinrich, Victor G. Lopez, Matthias A. Müller
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 |
|---|---|---|---|
| tune burn-in phase m* instead of baseline burn-in (ablation) | TBPTT LSTM · Silver-Box test (N=100) | test MSE: 0.291 -> 0.142 (-51%) | Improved |
| tune burn-in phase m* instead of baseline burn-in (ablation) | TBPTT LSTM · W-H test (N=200) | test MSE: 0.454 -> 0.476 (+5%) | Hurt |
| tune burn-in phase m* instead of baseline burn-in (ablation) | TBPTT LSTM · RLC test (N=100) | test MSE: 3.527 -> 1.093 (-69%) | Improved |
| tune burn-in phase m* instead of baseline burn-in (ablation) | TBPTT LSTM · Traffic test (N=192) | test MSE: 0.284 -> 0.276 (-3%) | No clear effect |
| tune burn-in phase m* instead of baseline burn-in (ablation) | TBPTT LSTM · Solar test (N=192) | test MSE: 0.211 -> 0.112 (-47%) | Improved |
Closest papers by meaning
- Memory-Efficient Backpropagation Through Time (NeurIPS 2016 · similarity 0.88)
- Training Recurrent Neural Networks Online by Learning Explicit State Variables (ICLR 2020 · similarity 0.88)
- Bifurcations and loss jumps in RNN training (NeurIPS 2023 · similarity 0.87)
- Training Recurrent Neural Networks via Forward Propagation Through Time (ICML 2021 · similarity 0.87)
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.86)
- TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting (NeurIPS 2026 · similarity 0.86)
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.
