Image de couverture de livre

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lim, Derek, Putterman, Theo Moe, Walters, Robin, Maron, Haggai, Jegelka, Stefanie
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
par: Putterman, Theo, et autres
Publié: (2024)

Graph Metanetworks for Processing Diverse Neural Architectures
par: Lim, Derek, et autres
Publié: (2023)

Symmetry in Neural Network Parameter Spaces
par: Zhao, Bo, et autres
Publié: (2025)

GradMetaNet: An Equivariant Architecture for Learning on Gradients
par: Gelberg, Yoav, et autres
Publié: (2025)

Learning from Historical Activations in Graph Neural Networks
par: Galron, Yaniv, et autres
Publié: (2026)

GRANOLA: Adaptive Normalization for Graph Neural Networks
par: Eliasof, Moshe, et autres
Publié: (2024)

Future Directions in the Theory of Graph Machine Learning
par: Morris, Christopher, et autres
Publié: (2024)

Efficient GNN Training Through Structure-Aware Randomized Mini-Batching
par: Balaji, Vignesh, et autres
Publié: (2025)

Survey on Generalization Theory for Graph Neural Networks
par: Vasileiou, Antonis, et autres
Publié: (2025)

Understanding and Improving Laplacian Positional Encodings For Temporal GNNs
par: Galron, Yaniv, et autres
Publié: (2025)

Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution
par: Wang, Rui, et autres
Publié: (2023)

Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results
par: Tahmasebi, Behrooz, et autres
Publié: (2020)

A Graph Meta-Network for Learning on Kolmogorov-Arnold Networks
par: Bar-Shalom, Guy, et autres
Publié: (2026)

Learning with Exact Invariances in Polynomial Time
par: Soleymani, Ashkan, et autres
Publié: (2025)

Geometric Algorithms for Neural Combinatorial Optimization with Constraints
par: Karalias, Nikolaos, et autres
Publié: (2025)

Improved Generalization of Weight Space Networks via Augmentations
par: Shamsian, Aviv, et autres
Publié: (2024)

The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE
par: Chernov, Andrei, et autres
Publié: (2025)

LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs
par: Li, Ang, et autres
Publié: (2025)

G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
par: Guo, Xiaojun, et autres
Publié: (2025)

Any-Subgroup Equivariant Networks via Symmetry Breaking
par: Goel, Abhinav, et autres
Publié: (2026)

How to Craft Backdoors with Unlabeled Data Alone?
par: Wang, Yifei, et autres
Publié: (2024)

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
par: Gatmiry, Khashayar, et autres
Publié: (2024)

Fairness Aware Reward Optimization
par: Choi, Ching Lam, et autres
Publié: (2026)

Are Graph Neural Networks Optimal Approximation Algorithms?
par: Yau, Morris, et autres
Publié: (2023)

Spanning the Visual Analogy Space with a Weight Basis of LoRAs
par: Manor, Hila, et autres
Publié: (2026)

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
par: Zhang, Qi, et autres
Publié: (2024)

On the Stability of Expressive Positional Encodings for Graphs
par: Huang, Yinan, et autres
Publié: (2023)

Scaling Attention via Feature Sparsity
par: Xie, Yan, et autres
Publié: (2026)

ReasonCACHE: Teaching LLMs To Reason Without Weight Updates
par: Gupta, Sharut, et autres
Publié: (2026)

AI Epidemiology: achieving explainable AI through expert oversight patterns
par: Tempest-Walters, Kit
Publié: (2025)

When More is Less: Understanding Chain-of-Thought Length in LLMs
par: Wu, Yuyang, et autres
Publié: (2025)

No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
par: Guo, Lixuan, et autres
Publié: (2026)

MatrixNet: Learning over symmetry groups using learned group representations
par: Laird, Lucas, et autres
Publié: (2025)

Reducing the Sensitivity of Neural Physics Simulators to Mesh Topology via Pretraining
par: Vaska, Nathan, et autres
Publié: (2025)

Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization
par: Boufalis, Odysseas, et autres
Publié: (2025)

An Information Criterion for Controlled Disentanglement of Multimodal Data
par: Wang, Chenyu, et autres
Publié: (2024)

Symmetry in the Wild: The Role of Equivariance in Neural Fluid Surrogates
par: Rygiel, Patryk, et autres
Publié: (2026)

Parameter Efficient Instruction Tuning: An Empirical Study
par: He, Pengfei
Publié: (2024)

Revisiting Training Scale: An Empirical Study of Token Count, Power Consumption, and Parameter Efficiency
par: Dwyer, Joe
Publié: (2026)

Divergence of Empirical Neural Tangent Kernel in Classification Problems
par: Yu, Zixiong, et autres
Publié: (2025)