Papers with Code 아카이브

Linear Mode Connectivity

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

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.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/9aze/ot_lmc

공식 코드

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport

https://github.com/alanjeffares/telescoping-lens

공식 코드

Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond

https://github.com/cptq/asymmetric-networks

공식 코드

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof

https://github.com/damienferbach/ot_lmc

공식 코드

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport

https://github.com/dennis-grinwald/floco

공식 코드

Federated Learning over Connected Modes

https://github.com/dyunis/spectral_dynamics

공식 코드

Approaching Deep Learning through the Spectral Dynamics of Weights

https://github.com/fagp/sinkhorn-rebasin

공식 코드

Re-basin via implicit Sinkhorn differentiation

https://github.com/imirzadeh/MC-SGD

공식 코드

Linear Mode Connectivity in Multitask and Continual Learning

https://github.com/link-er/layer-wise-lmc

공식 코드

Layer-wise Linear Mode Connectivity

https://github.com/rahimentezari/permutationinvariance

공식 코드

The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks

https://github.com/roberttlange/es-lottery

공식 코드

Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability

https://github.com/samuela/git-re-basin

공식 코드

Git Re-Basin: Merging Models modulo Permutation Symmetries

https://github.com/sixuli/wbfusionandlmc

공식 코드

Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural Networks

https://github.com/xingyuqu/rethink-re-basin

공식 코드

Vanishing Feature: Diagnosing Model Merging and Beyond

https://github.com/xingyuqu/vf

공식 코드

Vanishing Feature: Diagnosing Model Merging and Beyond

https://github.com/KarhouTam/FL-bench

Federated Learning over Connected Modes

https://github.com/facebookresearch/open_lth

Linear Mode Connectivity and the Lottery Ticket Hypothesis

https://github.com/gg-Dema/Git_merge

Git Re-Basin: Merging Models modulo Permutation Symmetries

https://github.com/luuyin/lottery-pools

Linear Mode Connectivity and the Lottery Ticket Hypothesis

https://github.com/themrzmaster/git-re-basin-pytorch

Git Re-Basin: Merging Models modulo Permutation Symmetries

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.