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

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

Paper

Similar papers

© 2026 NYSGPT2525 LLC