Copertina

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pham, Hoang, Ta, The-Anh, Jacobs, Tom, Burkholz, Rebekka, Tran-Thanh, Long
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation
di: Pham, Hoang, et al.
Pubblicazione: (2026)

Pay Attention to Small Weights
di: Zhou, Chao, et al.
Pubblicazione: (2025)

Flatness-aware Sequential Learning Generates Resilient Backdoors
di: Pham, Hoang, et al.
Pubblicazione: (2024)

Mask in the Mirror: Implicit Sparsification
di: Jacobs, Tom, et al.
Pubblicazione: (2024)

Revisiting LARS for Large Batch Training Generalization of Neural Networks
di: Do, Khoi, et al.
Pubblicazione: (2023)

The Neural Pruning Law Hypothesis
di: Barbulescu, Eugen, et al.
Pubblicazione: (2025)

HORST: Composing Optimizer Geometries for Sparse Transformer Training
di: Jacobs, Tom, et al.
Pubblicazione: (2026)

Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?
di: Jacobs, Tom, et al.
Pubblicazione: (2025)

Never Saddle for Reparameterized Steepest Descent as Mirror Flow
di: Jacobs, Tom, et al.
Pubblicazione: (2026)

On the Infinite Width and Depth Limits of Predictive Coding Networks
di: Innocenti, Francesco, et al.
Pubblicazione: (2026)

Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning
di: Nguyen, Ba Hoang Anh, et al.
Pubblicazione: (2026)

Adaptive Width Neural Networks
di: Errica, Federico, et al.
Pubblicazione: (2025)

Improving Graph Convolutional Networks with Transformer Layer in social-based items recommendation
di: Hoang, Thi Linh, et al.
Pubblicazione: (2024)

Tree-Sliced Wasserstein Distance with Nonlinear Projection
di: Tran, Thanh, et al.
Pubblicazione: (2025)

Constructing Decision Trees from Data Streams
di: Pham, Huy, et al.
Pubblicazione: (2024)

Bridging Domains through Subspace-Aware Model Merging
di: Chaves, Levy, et al.
Pubblicazione: (2026)

Understanding the Countably Infinite: Neural Network Models of the Successor Function and its Acquisition
di: Gupta, Vima, et al.
Pubblicazione: (2023)

Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$P Parametrization
di: Chen, Zixiang, et al.
Pubblicazione: (2025)

Sign-In to the Lottery: Reparameterizing Sparse Training From Scratch
di: Gadhikar, Advait, et al.
Pubblicazione: (2025)

Hyperbolic Aware Minimization: Implicit Bias for Sparsity
di: Jacobs, Tom, et al.
Pubblicazione: (2025)

Virtual Width Networks
di: Seed, et al.
Pubblicazione: (2025)

MP-PINN: A Multi-Phase Physics-Informed Neural Network for Epidemic Forecasting
di: Nguyen, Thang, et al.
Pubblicazione: (2024)

The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
di: Jiang, Fengqing, et al.
Pubblicazione: (2026)

Tree-Sliced Wasserstein Distance: A Geometric Perspective
di: Tran, Viet-Hoang, et al.
Pubblicazione: (2024)

Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks
di: Abedini, Samira, et al.
Pubblicazione: (2026)

Geometric Limits of Knowledge Distillation: A Minimum-Width Theorem via Superposition Theory
di: Sarkar, Nilesh, et al.
Pubblicazione: (2026)

Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think
di: Sernau, Luke
Pubblicazione: (2024)

NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
di: Kim, Jiwoo, et al.
Pubblicazione: (2026)

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing
di: Jamadandi, Adarsh, et al.
Pubblicazione: (2024)

Spherical Tree-Sliced Wasserstein Distance
di: Tran, Viet-Hoang, et al.
Pubblicazione: (2025)

Distance-Based Tree-Sliced Wasserstein Distance
di: Tran, Hoang V., et al.
Pubblicazione: (2025)

A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis
di: Kumar, Akash, et al.
Pubblicazione: (2025)

Identifying the Best Arm in the Presence of Global Environment Shifts
di: Srisawad, Phurinut, et al.
Pubblicazione: (2024)

Learning to Stop Overthinking at Test Time
di: Bao, Hieu Tran, et al.
Pubblicazione: (2025)

PruneSymNet: A Symbolic Neural Network and Pruning Algorithm for Symbolic Regression
di: Wu, Min, et al.
Pubblicazione: (2024)

Using Synthetic Data to estimate the True Error is theoretically and practically doable
di: Thanh, Hai Hoang, et al.
Pubblicazione: (2025)

A Dual Certificate Approach to Sparsity in Infinite-Width Shallow Neural Networks
di: Del Grande, Leonardo, et al.
Pubblicazione: (2026)

Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling
di: Tran, Dao, et al.
Pubblicazione: (2026)

Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
di: Tong, Anh, et al.
Pubblicazione: (2025)

Infinite Width Limits of Self Supervised Neural Networks
di: Fleissner, Maximilian, et al.
Pubblicazione: (2024)