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
Linear Mode Connectivity in Sparse Neural Networks0
Mode Combinability: Exploring Convex Combinations of Permutation Aligned Models0
Mode Connectivity and Data Heterogeneity of Federated Learning0
Model Assembly Learning with Heterogeneous Layer Weight Merging0
On Privileged and Convergent Bases in Neural Network Representations0
Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching0
Analyzing the Role of Permutation Invariance in Linear Mode Connectivity0
CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving0
CopRA: A Progressive LoRA Training Strategy0
Disentangling Linear Mode-Connectivity0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.