Research map / Optimization / Optimizers
Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming
Fei Wang, James Decker, Xilun Wu, Gregory Essertel, Tiark Rompf
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 |
|---|---|---|---|
| Lantern vs PyTorch on vanilla RNN and LSTM, batch size 20 | Lantern · vanilla RNN, LSTM | training time | Improved |
| Lantern vs PyTorch and TensorFlow on CNN, batch size 100 | Lantern · CNN | training time | No clear effect |
| Lantern vs PyTorch and TensorFlow Fold on recursive TreeLSTM | Lantern · TreeLSTM | training time | Improved |
| DyNet with autobatching vs Lantern on TreeLSTM | Lantern · TreeLSTM | training time: ~20% slower than DyNetB | Hurt |
| enable DyNet autobatching | DyNet · TreeLSTM | training time: approximately 40% speedup | Improved |
| larger batch sizes with DyNet autobatching | DyNet · TreeLSTM | training time | Hurt |
Closest papers by meaning
- Learning Differentiable Programs with Admissible Neural Heuristics (NeurIPS 2020 · similarity 0.86)
- Differentiable Dynamic Programming for Structured Prediction and Attention (ICML 2018 · similarity 0.85)
- On Lazy Training in Differentiable Programming (NeurIPS 2019 · similarity 0.85)
- BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning (NeurIPS 2024 · similarity 0.84)
- LPGD: A General Framework for Backpropagation through Embedded Optimization Layers (ICML 2024 · similarity 0.83)
- Taming Binarized Neural Networks and Mixed-Integer Programs (AAAI 2024 · similarity 0.82)
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.
