Imagen de Portada

Simultaneous linear connectivity of neural networks modulo permutation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sharma, Ekansh, Kwok, Devin, Denton, Tom, Roy, Daniel M., Rolnick, David, Dziugaite, Gintare Karolina
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse
por: Sharma, Ekansh, et al.
Publicado: (2024)

Dataset Difficulty and the Role of Inductive Bias
por: Kwok, Devin, et al.
Publicado: (2024)

Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization
por: Attias, Idan, et al.
Publicado: (2024)

On Traceability in $\ell_p$ Stochastic Convex Optimization
por: Voitovych, Sasha, et al.
Publicado: (2025)

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method
por: Baluta, Teodora, et al.
Publicado: (2024)

Less is More: Undertraining Experts Improves Model Upcycling
por: Horoi, Stefan, et al.
Publicado: (2025)

Data Selection for Transfer Unlearning
por: Sepahvand, Nazanin Mohammadi, et al.
Publicado: (2024)

Detoxifying LLMs via Representation Erasure-Based Preference Optimization
por: Sepahvand, Nazanin Mohammadi, et al.
Publicado: (2026)

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
por: Yang, Yu, et al.
Publicado: (2023)

Leveraging Function Space Aggregation for Federated Learning at Scale
por: Dhawan, Nikita, et al.
Publicado: (2023)

Improved Localized Machine Unlearning Through the Lens of Memorization
por: Torkzadehmahani, Reihaneh, et al.
Publicado: (2024)

The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
por: Kwok, Devin, et al.
Publicado: (2025)

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
por: Guo, Phillip, et al.
Publicado: (2024)

Soup to go: mitigating forgetting during continual learning with model averaging
por: Kleiman, Anat, et al.
Publicado: (2025)

Evaluating Interventional Reasoning Capabilities of Large Language Models
por: Kasetty, Tejas, et al.
Publicado: (2024)

Leveraging Per-Instance Privacy for Machine Unlearning
por: Sepahvand, Nazanin Mohammadi, et al.
Publicado: (2025)

SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning
por: Ohib, Riyasat, et al.
Publicado: (2024)

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
por: Siddiqui, Shoaib Ahmed, et al.
Publicado: (2025)

Torque-Aware Momentum
por: Malviya, Pranshu, et al.
Publicado: (2024)

The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
por: Jin, Tian, et al.
Publicado: (2025)

Continual Learning in Vision-Language Models via Aligned Model Merging
por: Sokar, Ghada, et al.
Publicado: (2025)

On permutation-invariant neural networks
por: Kimura, Masanari, et al.
Publicado: (2024)

Mixtures of Experts Unlock Parameter Scaling for Deep RL
por: Obando-Ceron, Johan, et al.
Publicado: (2024)

Temporal social network modeling of mobile connectivity data with graph neural networks
por: Jaskari, Joel, et al.
Publicado: (2025)

TQCompressor: improving tensor decomposition methods in neural networks via permutations
por: Abronin, V., et al.
Publicado: (2024)

Sobolev neural network with residual weighting as a surrogate in linear and non-linear mechanics
por: Kilicsoy, A. O. M., et al.
Publicado: (2024)

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
por: Inane, Ahmed Mehdi, et al.
Publicado: (2026)

Towards Climate Variable Prediction with Conditioned Spatio-Temporal Normalizing Flows
por: Winkler, Christina, et al.
Publicado: (2023)

SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training
por: Adnan, Mohammed, et al.
Publicado: (2026)

Equivariant non-linear maps for neural networks on homogeneous spaces
por: Nyholm, Elias, et al.
Publicado: (2025)

Mixture of Experts in a Mixture of RL settings
por: Willi, Timon, et al.
Publicado: (2024)

HyQuRP: Hybrid quantum-classical neural network with rotational and permutational equivariance
por: Park, Semin, et al.
Publicado: (2026)

Simultaneous estimation of connectivity and dimensionality in samples of networks
por: Jiang, Wenlong, et al.
Publicado: (2025)

Elimination-compensation pruning for fully-connected neural networks
por: Ballini, Enrico, et al.
Publicado: (2026)

Stable neural networks and connections to continuous dynamical systems
por: Ehrhardt, Matthias J., et al.
Publicado: (2025)

Uncertainty quantification in neural network classifiers -- a local linear approach
por: Malmström, Magnus, et al.
Publicado: (2023)

Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
por: Adnan, Mohammed, et al.
Publicado: (2025)

A universal linearized subspace refinement framework for neural networks
por: Cao, Wenbo, et al.
Publicado: (2026)

Posterior concentrations of fully-connected Bayesian neural networks with general priors on the weights
por: Kong, Insung, et al.
Publicado: (2024)

Graph neural networks for residential location choice: connection to classical logit models
por: Cheng, Zhanhong, et al.
Publicado: (2025)