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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 35 papers

TitleStatusHype
Understanding Mode Connectivity via Parameter Space Symmetry—0
CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving—0
Model Assembly Learning with Heterogeneous Layer Weight Merging—0
Finding Stable Subnetworks at Initialization with Dataset Distillation—0
Analyzing the Role of Permutation Invariance in Linear Mode Connectivity—0
The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE—0
Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & BeyondCode0
CopRA: A Progressive LoRA Training Strategy—0
The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse—0
Approaching Deep Learning through the Spectral Dynamics of WeightsCode1
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.