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 1–25 of 35 papers

TitleStatusHype
Git Re-Basin: Merging Models modulo Permutation SymmetriesCode2
Approaching Deep Learning through the Spectral Dynamics of WeightsCode1
Linear Mode Connectivity and the Lottery Ticket HypothesisCode1
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free TrainabilityCode1
The Role of Permutation Invariance in Linear Mode Connectivity of Neural NetworksCode1
Linear Mode Connectivity in Multitask and Continual LearningCode1
Re-basin via implicit Sinkhorn differentiationCode1
Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural NetworksCode0
Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & BeyondCode0
Layer-wise Linear Mode ConnectivityCode0
Proving Linear Mode Connectivity of Neural Networks via Optimal TransportCode0
Vanishing Feature: Diagnosing Model Merging and BeyondCode0
Federated Learning over Connected ModesCode0
The Empirical Impact of Neural Parameter Symmetries, or Lack ThereofCode0
Linear Mode Connectivity in Differentiable Tree Ensembles—0
Disentangling Linear Mode-Connectivity—0
Linear Mode Connectivity in Sparse Neural Networks—0
CopRA: A Progressive LoRA Training Strategy—0
Mode Combinability: Exploring Convex Combinations of Permutation Aligned Models—0
Mode Connectivity and Data Heterogeneity of Federated Learning—0
Model Assembly Learning with Heterogeneous Layer Weight Merging—0
On Privileged and Convergent Bases in Neural Network Representations—0
Training-time Neuron Alignment through Permutation Subspace for Improving Linear Mode Connectivity and Model Fusion—0
CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving—0
Understanding Mode Connectivity via Parameter Space Symmetry—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.