AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

Vincent Bürgin, Daniel Herbst, Ya-Wei Eileen Lin, Stefanie Jegelka

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Symmetry and equivariance in loss landscapes · 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
increase the fixed-weight scale sigma_F in W-asymmetric networks (center-dominated regime) (ablation)W-MLP and W-ResNet · MNIST / CIFAR-10 unaligned LMCunaligned LMC barrierImproved
break structural symmetry only (W-asymmetric with sigma_F=0) (ablation)W-MLP · MNIST unaligned LMCLMC barrierNo clear effect
align models by activation matching before interpolationsyre-ResNet · CIFAR-10 LMCLMC barrierImproved
align models by activation matching before interpolationW-asym. architectures with sigma_F=0 · MNIST / CIFAR-10 LMCLMC barrierImproved
increase sigma_F so identity permutation nearly matches optimal activation-matching permutation (ablation)W-MLP and W-ResNet · MNIST / CIFAR-10 activation matching objectiveactivation matching objectiveImproved
increase intrinsic data dimension k from 2 to 32 (sigma_F=1) (ablation)W-MLP on Gaussian mixture data · unaligned LMC midpoint train accuracy dropaccuracy drop (points): 46.4 -> 15.7 -> 6.1 for k=2, 8, 32Improved
increase input subspace coherence nu(U) in the F=0 setting (ablation)W-asym MLP (D~Bernoulli(0.15)) · synthetic ReLU(a+b) regressionLMC midpoint barrierImproved
use random mask D alone (without large fixed F) as symmetry breaker on incoherent dataW-asymmetric layers · theory (Thm 4.4)effective symmetry breakingNo clear effect
fix biases only (F varies in one intrinsic dimension)symmetry breaking via fixed biases · theory discussioneffective symmetry breakingNo clear effect

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