Image de couverture de livre

Theoretical Compression Bounds for Wide Multilayer Perceptrons

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cheairi, Houssam El, Gamarnik, David, Mazumder, Rahul
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Statistics Theory 68T07, 68W20
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Classification by Separating Hypersurfaces: An Entropic Approach
par: Arratia, Argimiro, et autres
Publié: (2025)

Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring
par: Antil, Harbir, et autres
Publié: (2025)

Random feature-based double Vovk-Azoury-Warmuth algorithm for online multi-kernel learning
par: Rokhlin, Dmitry B., et autres
Publié: (2025)

A hierarchical Vovk-Azoury-Warmuth forecaster with discounting for online regression in RKHS
par: Rokhlin, Dmitry B.
Publié: (2025)

Distributed Sparse Linear Regression under Communication Constraints
par: Fonseca, Rodney, et autres
Publié: (2023)

Ballistic Convergence in Hit-and-Run Monte Carlo and a Coordinate-free Randomized Kaczmarz Algorithm
par: Bou-Rabee, Nawaf, et autres
Publié: (2024)

Stealth edits to large language models
par: Sutton, Oliver J., et autres
Publié: (2024)

A Generalization Bound for a Family of Implicit Networks
par: Fung, Samy Wu, et autres
Publié: (2024)

Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos
par: Zhang, Haoyu, et autres
Publié: (2025)

ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models
par: Danieli, Federico, et autres
Publié: (2025)

Super-fast Rates of Convergence for Neural Network Classifiers under the Hard Margin Condition
par: Tepakbong, Nathanael, et autres
Publié: (2025)

On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing
par: Behboodi, Arash, et autres
Publié: (2024)

Credal and Interval Deep Evidential Classifications
par: Caprio, Michele, et autres
Publié: (2025)

The General Theory of Localization Methods
par: Song, Congwei
Publié: (2026)

Ranking Perspective for Tree-based Methods with Applications to Symbolic Feature Selection
par: Luo, Hengrui, et autres
Publié: (2024)

Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data
par: Pasini, Massimiliano Lupo, et autres
Publié: (2026)

Ergodic Generative Flows
par: Brunswic, Leo Maxime, et autres
Publié: (2025)

Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
par: Mitchell, Rupert, et autres
Publié: (2025)

Robust Tensor CUR Decompositions: Rapid Low-Tucker-Rank Tensor Recovery with Sparse Corruption
par: Cai, HanQin, et autres
Publié: (2023)

Towards a Rigorous Understanding of the Population Dynamics of the NSGA-III: Tight Runtime Bounds
par: Opris, Andre
Publié: (2025)

Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
par: Hashimoto, Ichiro
Publié: (2025)

Asymptotics of Stochastic Gradient Descent with Dropout Regularization in Linear Models
par: Li, Jiaqi, et autres
Publié: (2024)

CompressedScaffnew: The First Theoretical Double Acceleration of Communication from Local Training and Compression in Distributed Optimization
par: Condat, Laurent, et autres
Publié: (2022)

Nonparametric estimation of a factorizable density using diffusion models
par: Kwon, Hyeok Kyu, et autres
Publié: (2025)

Model Parallel Training and Transfer Learning for Convolutional Neural Networks by Domain Decomposition
par: Klawonn, Axel, et autres
Publié: (2024)

Domain-decomposed image classification algorithms using linear discriminant analysis and convolutional neural networks
par: Klawonn, Axel, et autres
Publié: (2024)

Algorithmic Universality, Low-Degree Polynomials, and Max-Cut in Sparse Random Graphs
par: Cheairi, Houssam El, et autres
Publié: (2024)

Estimating Coverage in Streams via a Modified CVM Method
par: Hernandez-Suarez, Carlos
Publié: (2025)

An operator learning perspective on parameter-to-observable maps
par: Huang, Daniel Zhengyu, et autres
Publié: (2024)

Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression
par: Jiang, Wei, et autres
Publié: (2026)

Adversarial Subspace Generation for Outlier Detection in High-Dimensional Data
par: Cribeiro-Ramallo, Jose, et autres
Publié: (2025)

A Domain Decomposition-Based CNN-DNN Architecture for Model Parallel Training Applied to Image Recognition Problems
par: Klawonn, Axel, et autres
Publié: (2023)

Error Bounds for Learning with Vector-Valued Random Features
par: Lanthaler, Samuel, et autres
Publié: (2023)

Functional Similarity Metric for Neural Networks: Overcoming Parametric Ambiguity via Activation Region Analysis
par: Hennadii, Kutomanov
Publié: (2026)

Subgroups of Cyclically Amalgamated Free Products
par: Kreuzer, Martin, et autres
Publié: (2025)

Adaptive monotonicity testing in sublinear time
par: Li, Housen, et autres
Publié: (2025)

Exact recovery for seeded graph matching
par: Fraiman, Nicolas, et autres
Publié: (2026)

Progressive Feedforward Collapse of ResNet Training
par: Wang, Sicong, et autres
Publié: (2024)

Shortest Paths without a Map, but with an Entropic Regularizer
par: Bubeck, Sébastien, et autres
Publié: (2022)

Optimal In-context Adaptivity and Distributional Robustness of Transformers
par: Ma, Tianyi, et autres
Publié: (2025)