knowledge-base-4
Linear Mode Connectivity
3260 papers • 126 benchmarks • 313 datasets
Linear Mode Connectivity refers to the relationship between input and output variables in a linear regression model. In a linear regression model, input variables are combined with weights to predict output variables. Understanding the linear model connectivity can help interpret model results and identify which input variables are most important for predicting output variables.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in linear-mode-connectivity-4
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find linear-mode-connectivity-4 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
Linear Mode Connectivity and the Lottery Ticket Hypothesis
Jonathan Frankle, Michael Carbin, G. Dziugaite, Daniel M. Roy•Tue Dec 10 2019
This work finds that standard vision models become stable to SGD noise in this way early in training, and uses this technique to study iterative magnitude pruning (IMP), the procedure used by work on the lottery ticket hypothesis to identify subnetworks that could have trained in isolation to full accuracy.
718