AI Paper Atlas

Research map / Point clouds / Point cloud classification

Semi-flat minima and saddle points by embedding neural networks to overparameterization

Kenji Fukumizu, Shoichiro Yamaguchi, Yoh-ichi Mototake, Mirai Tanaka

NeurIPS 2019 · Point clouds › Point cloud classification · approach: Equivariant point cloud networks · 3 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
Add inactive units to a ReLU networkA wider ReLU network embedding a narrower local minimum · Training error landscapeminimum statusImproved
Add inactive units to a ReLU networkA wider ReLU network · Training error landscapeflat directionsImproved
Replace ReLU with a smooth activation for inactive-unit embeddingA wider network embedding a zero-training-error solution · Training error landscapeflat directionsHurt
Replicate a unit in a smooth networkA wider smooth network · Training error landscapeminimum statusHurt
Replicate a unit in a ReLU networkA wider ReLU network · Training error landscapeminimum statusHurt
Use inactive units without ensuring their outgoing weights are zero (ablation)Smooth-network embedding · Training error landscapestationarityHurt
Use inactive propagation without also making surplus units inactive (ablation)Smooth-network embedding · Training error landscapestationarityHurt
Add inactive units to a smooth network instead of replicating a unit (ablation)Embedding a minimum in a wider smooth network · Training error landscapeminimum statusMixed
Increase surplus-unit countReLU versus tanh networks fitted with inactive units · Generalization errorgeneralization error trendMixed
Use ReLU rather than smooth activation for zero-error inactive-unit embeddingsOverparameterized networks with the same number of surplus units · Generalization error boundPAC-Bayes upper boundImproved

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