Copertina

Pruning Deep Neural Networks via a Combination of the Marchenko-Pastur Distribution and Regularization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Berlyand, Leonid, Bourdais, Theo, Owhadi, Houman, Shmalo, Yitzchak
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Enhancing Accuracy in Deep Learning Using Random Matrix Theory
di: Berlyand, Leonid, et al.
Pubblicazione: (2023)

Minimal Variance Model Aggregation: A principled, non-intrusive, and versatile integration of black box models
di: Bourdais, Théo, et al.
Pubblicazione: (2024)

Discovering Algorithms with Computational Language Processing
di: Bourdais, Theo, et al.
Pubblicazione: (2025)

A Dynamics-Informed Gaussian Process Framework for 2D Stochastic Navier-Stokes via Quasi-Gaussianity
di: Hamzi, Boumediene, et al.
Pubblicazione: (2025)

Codiscovering graphical structure and functional relationships within data: A Gaussian Process framework for connecting the dots
di: Bourdais, Théo, et al.
Pubblicazione: (2023)

Operator Learning at Machine Precision
di: Bacho, Aras, et al.
Pubblicazione: (2025)

ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks
di: Zhang, Zhizhen, et al.
Pubblicazione: (2026)

Kernel Methods for Some Transport Equations with Application to Learning Kernels for the Approximation of Koopman Eigenfunctions: A Unified Approach via Variational Methods, Green's Functions and the Method of Characteristics
di: Hamzi, Boumediene, et al.
Pubblicazione: (2026)

Solving Roughly Forced Nonlinear PDEs via Misspecified Kernel Methods and Neural Networks
di: Baptista, Ricardo, et al.
Pubblicazione: (2025)

Bridging Algorithmic Information Theory and Machine Learning: A New Approach to Kernel Learning
di: Hamzi, Boumediene, et al.
Pubblicazione: (2023)

KROM: Kernelized Reduced Order Modeling
di: Bacho, Aras, et al.
Pubblicazione: (2026)

Kolmogorov n-Widths for Multitask Physics-Informed Machine Learning (PIML) Methods: Towards Robust Metrics
di: Penwarden, Michael, et al.
Pubblicazione: (2024)

Kernel Methods for Stochastic Dynamical Systems with Application to Koopman Eigenfunctions: Feynman-Kac Representations and RKHS Approximation
di: Hamzi, Boumediene, et al.
Pubblicazione: (2026)

Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
di: Romanov, Elad, et al.
Pubblicazione: (2024)

Adaptive Kernel Selection for Kernelized Diffusion Maps
di: Aboussaad, Othmane, et al.
Pubblicazione: (2026)

Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows
di: Sharma, Ramansh, et al.
Pubblicazione: (2026)

Black Holes and Marchenko-Pastur Distribution
di: Mück, Wolfgang
Pubblicazione: (2024)

Operator Learning with Gaussian Processes
di: Mora, Carlos, et al.
Pubblicazione: (2024)

Kernel Sum of Squares for Data Adapted Kernel Learning of Dynamical Systems from Data: A global optimization approach
di: Lengyel, Daniel, et al.
Pubblicazione: (2024)

Asymptotic behavior of eigenvalues of large rank perturbations of large random matrices
di: Afanasiev, Ievgenii, et al.
Pubblicazione: (2025)

Learning dynamical systems from data: A simple cross-validation perspective, part III: Irregularly-Sampled Time Series
di: Lee, Jonghyeon, et al.
Pubblicazione: (2021)

Sparse Cholesky Factorization for Solving Nonlinear PDEs via Gaussian Processes
di: Chen, Yifan, et al.
Pubblicazione: (2023)

Gaussian Measures Conditioned on Nonlinear Observations: Consistency, MAP Estimators, and Simulation
di: Chen, Yifan, et al.
Pubblicazione: (2024)

Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs
di: Yuan, Qiwei, et al.
Pubblicazione: (2025)

Toward Efficient Kernel-Based Solvers for Nonlinear PDEs
di: Xu, Zhitong, et al.
Pubblicazione: (2024)

Data-efficient Kernel Methods for Learning Hamiltonian Systems
di: Jalalian, Yasamin, et al.
Pubblicazione: (2025)

Solving Functional PDEs with Gaussian Processes and Applications to Functional Renormalization Group Equations
di: Yang, Xianjin, et al.
Pubblicazione: (2025)

Deep Neural Networks are Adaptive to Function Regularity and Data Distribution in Approximation and Estimation
di: Liu, Hao, et al.
Pubblicazione: (2024)

Concurrent Training and Layer Pruning of Deep Neural Networks
di: Guenter, Valentin Frank Ingmar, et al.
Pubblicazione: (2024)

Bilevel optimization for learning hyperparameters: Application to solving PDEs and inverse problems with Gaussian processes
di: Nelsen, Nicholas H., et al.
Pubblicazione: (2025)

Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysis
di: Jalalian, Yasamin, et al.
Pubblicazione: (2025)

Dictionary learning for Kernel EDMD
di: Bolager, Erik Lien, et al.
Pubblicazione: (2026)

$q$-deformation of the Marchenko-Pastur law
di: Byun, Sung-Soo, et al.
Pubblicazione: (2026)

A New Branch-and-Bound Pruning Framework for $\ell_0$-Regularized Problems
di: Guyard, Theo, et al.
Pubblicazione: (2024)

Kernel Methods for the Approximation of the Eigenfunctions of the Koopman Operator
di: Lee, Jonghyeon, et al.
Pubblicazione: (2024)

Pruning Deep Convolutional Neural Network Using Conditional Mutual Information
di: Vu-Van, Tien, et al.
Pubblicazione: (2024)

Quantization-Aware Regularizers for Deep Neural Networks Compression
di: Malchiodi, Dario, et al.
Pubblicazione: (2026)

Adaptive Tabu Dropout for Regularization of Deep Neural Network
di: Hasan, Md. Tarek, et al.
Pubblicazione: (2024)

Lattice-based Deep Neural Networks: Regularity and Tailored Regularization
di: Keller, Alexander, et al.
Pubblicazione: (2026)

Diffeomorphic Measure Matching with Kernels for Generative Modeling
di: Pandey, Biraj, et al.
Pubblicazione: (2024)