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 1–35 of 35 papers

TitleStatusHype
Git Re-Basin: Merging Models modulo Permutation SymmetriesCode2
The Role of Permutation Invariance in Linear Mode Connectivity of Neural NetworksCode1
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free TrainabilityCode1
Linear Mode Connectivity in Multitask and Continual LearningCode1
Re-basin via implicit Sinkhorn differentiationCode1
Linear Mode Connectivity and the Lottery Ticket HypothesisCode1
Approaching Deep Learning through the Spectral Dynamics of WeightsCode1
Improving Group Connectivity for Generalization of Federated Deep Learning—0
Landscaping Linear Mode Connectivity—0
Linear Mode Connectivity in Differentiable Tree Ensembles—0
Linear Mode Connectivity in Sparse Neural Networks—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
Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching—0
Analyzing the Role of Permutation Invariance in Linear Mode Connectivity—0
CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving—0
CopRA: A Progressive LoRA Training Strategy—0
Disentangling Linear Mode-Connectivity—0
Finding Stable Subnetworks at Initialization with Dataset Distillation—0
High-dimensional manifold of solutions in neural networks: insights from statistical physics—0
The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE—0
The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse—0
Towards Understanding Iterative Magnitude Pruning: Why Lottery Tickets Win—0
Training-time Neuron Alignment through Permutation Subspace for Improving Linear Mode Connectivity and Model Fusion—0
Understanding Mode Connectivity via Parameter Space Symmetry—0
Unveiling the Dynamics of Information Interplay in Supervised Learning—0
Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural NetworksCode0
Proving Linear Mode Connectivity of Neural Networks via Optimal TransportCode0
Layer-wise Linear Mode ConnectivityCode0
Vanishing Feature: Diagnosing Model Merging and BeyondCode0
Federated Learning over Connected ModesCode0
The Empirical Impact of Neural Parameter Symmetries, or Lack ThereofCode0
Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & BeyondCode0
Show:102550

No leaderboard results yet.