Copertina

Linear Mode Connectivity in Sparse Neural Networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	McDermott, Luke, Cummings, Daniel
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimization-Induced Dynamics of Lipschitz Continuity in Neural Networks
di: Luo, Róisín, et al.
Pubblicazione: (2025)

Text Conditioned Symbolic Drumbeat Generation using Latent Diffusion Models
di: Jajoria, Pushkar, et al.
Pubblicazione: (2024)

Unveiling Mode Connectivity in Graph Neural Networks
di: Li, Bingheng, et al.
Pubblicazione: (2025)

LoLA: Low-Rank Linear Attention With Sparse Caching
di: McDermott, Luke, et al.
Pubblicazione: (2025)

Embedding Compression for Efficient Re-Identification
di: McDermott, Luke
Pubblicazione: (2024)

ACES: Automatic Cohort Extraction System for Event-Stream Datasets
di: Xu, Justin, et al.
Pubblicazione: (2024)

Finding Stable Subnetworks at Initialization with Dataset Distillation
di: McDermott, Luke, et al.
Pubblicazione: (2025)

Sparse Decomposition of Graph Neural Networks
di: Hu, Yaochen, et al.
Pubblicazione: (2024)

Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
di: Di Carlo, Luca, et al.
Pubblicazione: (2025)

Advancing On-Device Neural Network Training with TinyPropv2: Dynamic, Sparse, and Efficient Backpropagation
di: Rüb, Marcus, et al.
Pubblicazione: (2024)

Unveiling the Power of Sparse Neural Networks for Feature Selection
di: Atashgahi, Zahra, et al.
Pubblicazione: (2024)

Playing the Lottery With Concave Regularizers for Sparse Trainable Neural Networks
di: Fracastoro, Giulia, et al.
Pubblicazione: (2025)

Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks
di: Dorszewski, Teresa, et al.
Pubblicazione: (2024)

Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphs
di: He, Shuqi, et al.
Pubblicazione: (2024)

mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks
di: Mishra, Subhankar
Pubblicazione: (2026)

Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations
di: Cunegatti, Elia, et al.
Pubblicazione: (2023)

Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability
di: Bereska, Leonard, et al.
Pubblicazione: (2025)

Diagnosis of Fuel Cell Health Status with Deep Sparse Auto-Encoder Neural Network
di: Fei, Chenyan, et al.
Pubblicazione: (2025)

Displacement-Sparse Neural Optimal Transport
di: Chen, Peter, et al.
Pubblicazione: (2025)

A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
di: Ganju, Atul, et al.
Pubblicazione: (2026)

Dynamic DropConnect: Enhancing Neural Network Robustness through Adaptive Edge Dropping Strategies
di: Yang, Yuan-Chih, et al.
Pubblicazione: (2025)

NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks
di: Reneau, Alex, et al.
Pubblicazione: (2025)

Probabilistically Tightened Linear Relaxation-based Perturbation Analysis for Neural Network Verification
di: Marzari, Luca, et al.
Pubblicazione: (2025)

ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back Propagation
di: Zhong, Lujia, et al.
Pubblicazione: (2024)

Subjectivity in Unsupervised Machine Learning Model Selection
di: Chen, Wanyi, et al.
Pubblicazione: (2023)

Lecture Notes on Linear Neural Networks: A Tale of Optimization and Generalization in Deep Learning
di: Cohen, Nadav, et al.
Pubblicazione: (2024)

Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
di: Lim, Jinwoo, et al.
Pubblicazione: (2026)

Mode-Aware Non-Linear Tucker Autoencoder for Tensor-based Unsupervised Learning
di: Zheng, Junjing, et al.
Pubblicazione: (2025)

INSPIRE-GNN: Intelligent Sensor Placement to Improve Sparse Bicycling Network Prediction via Reinforcement Learning Boosted Graph Neural Networks
di: Gupta, Mohit, et al.
Pubblicazione: (2025)

Diversity-Aware Adaptive Collocation for Physics-Informed Neural Networks via Sparse QUBO Optimization and Hybrid Coresets
di: Salloum, Hadi, et al.
Pubblicazione: (2026)

A Lower Bound for the Number of Linear Regions of Ternary ReLU Regression Neural Networks
di: Nakahara, Yuta, et al.
Pubblicazione: (2025)

ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks
di: Chaudhry, Zan, et al.
Pubblicazione: (2024)

Unified Sparse-Matrix Representations for Diverse Neural Architectures
di: Zhu, Yuzhou
Pubblicazione: (2025)

Optimizer-Induced Mode Connectivity: From AdamW to Muon
di: Zhang, Fangzhao, et al.
Pubblicazione: (2026)

The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
di: Cha, Taehun, et al.
Pubblicazione: (2026)

Spatio-Spectral Graph Neural Networks
di: Geisler, Simon, et al.
Pubblicazione: (2024)

Foundation Model of Electronic Medical Records for Adaptive Risk Estimation
di: Renc, Pawel, et al.
Pubblicazione: (2025)

TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks
di: Maheri, Mohammad M, et al.
Pubblicazione: (2025)

BikeVAE-GNN: A Variational Autoencoder-Augmented Hybrid Graph Neural Network for Sparse Bicycle Volume Estimation
di: Gupta, Mohit, et al.
Pubblicazione: (2025)

Learning to Solve Combinatorial Optimization under Positive Linear Constraints via Non-Autoregressive Neural Networks
di: Wang, Runzhong, et al.
Pubblicazione: (2024)