Pith. sign in

REVIEW 13 cited by

The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.06296 v2 pith:OPK6D324 submitted 2021-10-12 cs.LG

The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks

classification cs.LG
keywords conjectureinvariancelinearnetworksneuralpermutationaccountalthough
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this paper, we conjecture that if the permutation invariance of neural networks is taken into account, SGD solutions will likely have no barrier in the linear interpolation between them. Although it is a bold conjecture, we show how extensive empirical attempts fall short of refuting it. We further provide a preliminary theoretical result to support our conjecture. Our conjecture has implications for lottery ticket hypothesis, distributed training, and ensemble methods.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Editing Models with Task Arithmetic

    cs.LG 2022-12 accept novelty 8.0

    Task vectors from weight differences allow arithmetic operations to edit pre-trained models, improving multiple tasks simultaneously and enabling analogical inference on unseen tasks.

  2. Cross-Trajectory Chimera Interventions Reveal Dissociable Roles of Weight Magnitude and Direction in Grokking

    cs.LG 2026-07 conditional novelty 7.0

    In grokking modular arithmetic, weight direction portably carries circuit identity across independent runs while weight norm only sets susceptibility to overwrite and a weak delay effect.

  3. Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs

    cs.CR 2026-06 unverdicted novelty 7.0

    Tiered Language Models use a secret key to induce an alternative computation graph over shared weights, enabling private capabilities in the keyed mode while the public mode shows none.

  4. Less is MoE: Trimming Experts in Domain-Specialist Language Models

    cs.LG 2026-06 unverdicted novelty 7.0

    Fisher-MoE prunes sparse intermediate dimensions in MoE FFNs ranked by Fisher importance, delivering 50% compression that preserves capability while cutting memory ~45% and raising throughput 21%.

  5. Understanding Layer Patching in Model Size Interpolation

    cs.LG 2026-07 conditional novelty 6.0

    Optimal layer-patching order for boomerang distillation is a shortest path on a KL-weighted Boolean lattice; greedy KLPatch and simple sequential orders often yield near-optimal interpolations.

  6. Motion-Compensated Weight Compression

    cs.CV 2026-05 unverdicted novelty 6.0

    MCWC aligns permutation-symmetric blocks across layers to enable sequential prediction and residual entropy coding, improving rate-accuracy tradeoffs versus quantization and prior codecs on language and vision models.

  7. Unlocking the Potential of Continual Model Merging: An ODE Perspective

    cs.LG 2026-05 unverdicted novelty 6.0

    ODE-M traces low-loss connecting paths via time-dependent velocity fields and barrier constraints to improve controllability and reduce forgetting in continual model merging.

  8. Unlocking the Potential of Continual Model Merging: An ODE Perspective

    cs.LG 2026-05 unverdicted novelty 6.0

    ODE-M formulates continual model merging as a barrier-aware ODE trajectory in parameter space, using first-order feedback and a utility-aware schedule to balance retained knowledge and new task performance.

  9. Unlocking the Potential of Continual Model Merging: An ODE Perspective

    cs.LG 2026-05 unverdicted novelty 6.0

    Introduces ODE-M, an ODE-based merging method for continual model merging that follows low-loss connecting paths to mitigate catastrophic forgetting.

  10. Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers

    cs.LG 2026-06 unverdicted novelty 5.0

    A bidirectional optimization method using parameterized transformations enables near-zero loss barriers for linear mode connectivity in medium-scale language models and small barriers in billion-parameter transformers.

  11. Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics

    cs.LG 2026-05 unverdicted novelty 5.0

    DiMS is a physics-inspired dynamical sampler guaranteed to exactly sample reparameterization-invariant minimum level sets in neural network loss landscapes.

  12. The Platonic Representation Hypothesis

    cs.LG 2024-05 unverdicted novelty 5.0

    Representations learned by large AI models are converging toward a shared statistical model of reality.

  13. Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City

    cs.CV 2026-06 unverdicted novelty 4.0

    Humans and VLMs diverge in VQA responses on driving footage, with human answers consistent across origins and no strong geography modulation observed, likely due to high OOD nature.