SOTAVerified

Linear Mode Connectivity

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.

Papers

Showing 1120 of 35 papers

TitleStatusHype
Finding Stable Subnetworks at Initialization with Dataset Distillation0
Analyzing the Role of Permutation Invariance in Linear Mode Connectivity0
The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE0
Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & BeyondCode0
CopRA: A Progressive LoRA Training Strategy0
The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse0
Landscaping Linear Mode Connectivity0
Unveiling the Dynamics of Information Interplay in Supervised Learning0
The Empirical Impact of Neural Parameter Symmetries, or Lack ThereofCode0
Linear Mode Connectivity in Differentiable Tree Ensembles0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.