Image de couverture de livre

Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ito, Akira, Yamada, Masanori, Kumagai, Atsutoshi
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
par: Ito, Akira, et autres
Publié: (2025)

Analyzing the Role of Permutation Invariance in Linear Mode Connectivity
par: Zhan, Keyao, et autres
Publié: (2025)

Learning Unbiased Permutations via Flow Matching
par: Min, Yimeng, et autres
Publié: (2026)

Meta-learning for Positive-unlabeled Classification
par: Kumagai, Atsutoshi, et autres
Publié: (2024)

Monte Carlo Permutation Search
par: Cazenave, Tristan
Publié: (2025)

Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment
par: Takahashi, Hiroshi, et autres
Publié: (2026)

Mechanistic Permutability: Match Features Across Layers
par: Balagansky, Nikita, et autres
Publié: (2024)

Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation to Multiple Image Corruptions
par: Adachi, Kazuki, et autres
Publié: (2022)

On the Expressive Power of Permutation-Equivariant Weight-Space Networks
par: Dayan, Adir, et autres
Publié: (2026)

Connecting Permutation Equivariant Neural Networks and Partition Diagrams
par: Pearce-Crump, Edward
Publié: (2022)

Permutation Decision Trees
par: B, Harikrishnan N, et autres
Publié: (2023)

Structure As Search: Unsupervised Permutation Learning for Combinatorial Optimization
par: Min, Yimeng, et autres
Publié: (2025)

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data
par: Takahashi, Hiroshi, et autres
Publié: (2024)

Finite-Sample Inference for Sparsely Permuted Linear Regression
par: Ota, Hirofumi, et autres
Publié: (2026)

Meta-learning Representations for Learning from Multiple Annotators
par: Kumagai, Atsutoshi, et autres
Publié: (2025)

Permutation Inference for Canonical Correlation Analysis
par: Winkler, Anderson M., et autres
Publié: (2020)

Test-time Adaptation for Regression by Subspace Alignment
par: Adachi, Kazuki, et autres
Publié: (2024)

Geometry of Linear Neural Networks: Equivariance and Invariance under Permutation Groups
par: Kohn, Kathlén, et autres
Publié: (2023)

Permutation-Invariant Spectral Learning via Dyson Diffusion
par: Schwarz, Tassilo, et autres
Publié: (2025)

PPFS: Predictive Permutation Feature Selection
par: Hassan, Atif, et autres
Publié: (2021)

Fair Feature Importance Scores via Feature Occlusion and Permutation
par: Little, Camille, et autres
Publié: (2026)

Tight Compression: Compressing CNN Through Fine-Grained Pruning and Weight Permutation for Efficient Implementation
par: Chen, Xizi, et autres
Publié: (2021)

Learning Permutation Distributions via Reflected Diffusion on Ranks
par: He, Sizhuang, et autres
Publié: (2026)

Differentially Private Permutation Tests: Applications to Kernel Methods
par: Kim, Ilmun, et autres
Publié: (2023)

Neural Networks Trained by Weight Permutation are Universal Approximators
par: Cai, Yongqiang, et autres
Publié: (2024)

Continuous Optimization for Feature Selection with Permutation-Invariant Embedding and Policy-Guided Search
par: Liu, Rui, et autres
Publié: (2025)

Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
par: Takahashi, Hiroshi, et autres
Publié: (2025)

Finite-Sample Identification of Linear Regression Models with Residual-Permuted Sums
par: Szentpéteri, Szabolcs, et autres
Publié: (2024)

PLeaS -- Merging Models with Permutations and Least Squares
par: Nasery, Anshul, et autres
Publié: (2024)

Restricted Block Permutation for Two-Sample Testing
par: Ho, Jungwoo
Publié: (2025)

Permutation-Symmetrized Diffusion for Unconditional Molecular Generation
par: Ko, Gyeonghoon, et autres
Publié: (2026)

Trustworthy Feature Importance Avoids Unrestricted Permutations
par: Borgonovo, Emanuele, et autres
Publié: (2026)

Learning Permutation from Structure Without Supervision
par: Eisenberg, Ran, et autres
Publié: (2026)

Toward Falsifying Causal Graphs Using a Permutation-Based Test
par: Eulig, Elias, et autres
Publié: (2023)

Landscaping Linear Mode Connectivity
par: Singh, Sidak Pal, et autres
Publié: (2024)

Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
par: Yamashita, Tomoya, et autres
Publié: (2025)

AI Methods for Permutation Circuit Synthesis Across Generic Topologies
par: Villar, Victor, et autres
Publié: (2025)

Learning Permutation-invariant Macroscopic Dynamics
par: Han, Zhichao, et autres
Publié: (2026)

PEARL: Towards Permutation-Resilient LLMs
par: Chen, Liang, et autres
Publié: (2025)

A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond
par: Li, Yipeng, et autres
Publié: (2025)