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
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
Landscaping Linear Mode Connectivity—0
Unveiling the Dynamics of Information Interplay in Supervised Learning—0
The Empirical Impact of Neural Parameter Symmetries, or Lack ThereofCode0
Linear Mode Connectivity in Differentiable Tree Ensembles—0
Federated Learning over Connected ModesCode0
Improving Group Connectivity for Generalization of Federated Deep Learning—0
Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching—0
Vanishing Feature: Diagnosing Model Merging and BeyondCode0
Training-time Neuron Alignment through Permutation Subspace for Improving Linear Mode Connectivity and Model Fusion—0
Disentangling Linear Mode-Connectivity—0
Proving Linear Mode Connectivity of Neural Networks via Optimal TransportCode0
Linear Mode Connectivity in Sparse Neural Networks—0
Mode Connectivity and Data Heterogeneity of Federated Learning—0
High-dimensional manifold of solutions in neural networks: insights from statistical physics—0
Mode Combinability: Exploring Convex Combinations of Permutation Aligned Models—0
On Privileged and Convergent Bases in Neural Network Representations—0
Layer-wise Linear Mode ConnectivityCode0
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free TrainabilityCode1
Re-basin via implicit Sinkhorn differentiationCode1
Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural NetworksCode0
Git Re-Basin: Merging Models modulo Permutation SymmetriesCode2
The Role of Permutation Invariance in Linear Mode Connectivity of Neural NetworksCode1
Towards Understanding Iterative Magnitude Pruning: Why Lottery Tickets Win—0
Linear Mode Connectivity in Multitask and Continual LearningCode1
Linear Mode Connectivity and the Lottery Ticket HypothesisCode1
Show:102550

No leaderboard results yet.