AI Paper Atlas

Research map / Optimization / Optimizers

Splitting Steepest Descent for Growing Neural Architectures

Lemeng Wu, Dilin Wang, Qiang Liu

NeurIPS 2019 · Optimization › Optimizers · approach: Constrained and non-backprop training · 19 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
Use progressive neuron splitting to grow a compact DS-CNNCompact DS-CNN · Google Speech Commandsaccuracy: 94.85 -> 95.36Improved
Use progressive neuron splitting instead of the DS-CNN baselineCompact DS-CNN · Google Speech CommandsParams (K): 413.7 -> 282.6Improved
Use progressive neuron splitting instead of the DS-CNN baselineCompact DS-CNN · Google Speech CommandsOps (M): 56.9 -> 39.2Improved
Choose neurons with the most negative splitting indexes and split along their minimum-eigenvalue directionsProgressive neuron-splitting method · Toy RBF neural networklossImproved

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