SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.06296 · 2021

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2110.06296")
get_code_for_paper("2110.06296")
have("2110.06296")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2110.06296.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2110.06296.svg)](https://syntology.ai/paper/2110.06296)

Connect an agent — have() is free.