AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity

Zhanpeng Zhou, Yongyi Yang, Xiaojiang Yang, Junchi Yan, Wei Hu

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 0 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 spawning to obtain LMC-connected modes instead of independently trained modesneural networks trained with spawning · MNIST, CIFAR-10, and Tiny-ImageNet; reported architectures1 - cosine similarity between interpolated-model features and interpolated endpoImproved
use permutation matching to obtain LMC-connected modes instead of leaving independently trained modes unalignedneural networks trained with permutation matching · CIFAR-10 and other reported image-classification settings1 - cosine similarity between interpolated-model features and interpolated endpoImproved
use spawning to obtain linearly connected modes instead of independently trained modesReLU networks trained with spawning · Reported datasets and architecturesweak-additivity distanceImproved
apply activation matching or weight matching before comparing independently trained modesGit Re-Basin permutation method · Reported datasets and architecturesweak-additivity distanceImproved
use spawning or permutation to obtain LLFC modes instead of comparing independently trained modesneural networks trained with spawning or permutation · MNIST and CIFAR-10; reported architecturescommutativity distanceImproved

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