AI Paper Atlas

Research map / Optimization / Optimizers

Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming

Fei Wang, James Decker, Xilun Wu, Gregory Essertel, Tiark Rompf

NeurIPS 2018 · Optimization › Optimizers · approach: Constrained and non-backprop training · 18 citations (OpenAlex)

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 changedWhereMeasuredEffect
Lantern vs PyTorch on vanilla RNN and LSTM, batch size 20Lantern · vanilla RNN, LSTMtraining timeImproved
Lantern vs PyTorch and TensorFlow on CNN, batch size 100Lantern · CNNtraining timeNo clear effect
Lantern vs PyTorch and TensorFlow Fold on recursive TreeLSTMLantern · TreeLSTMtraining timeImproved
DyNet with autobatching vs Lantern on TreeLSTMLantern · TreeLSTMtraining time: ~20% slower than DyNetBHurt
enable DyNet autobatchingDyNet · TreeLSTMtraining time: approximately 40% speedupImproved
larger batch sizes with DyNet autobatchingDyNet · TreeLSTMtraining timeHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy