Copertina

Overparametrized linear dimensionality reductions: From projection pursuit to two-layer neural networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Montanari, Andrea, Zhou, Kangjie
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Learning time-scales in two-layers neural networks
di: Berthier, Raphaël, et al.
Pubblicazione: (2023)

Which exceptional low-dimensional projections of a Gaussian point cloud can be found in polynomial time?
di: Montanari, Andrea, et al.
Pubblicazione: (2024)

Tractability from overparametrization: The example of the negative perceptron
di: Montanari, Andrea, et al.
Pubblicazione: (2021)

Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
di: Grontas, Panagiotis D., et al.
Pubblicazione: (2025)

Generalization error property of infoGAN for two-layer neural network
di: Hasan, Mahmud, et al.
Pubblicazione: (2023)

Overparametrized models with posterior drift
di: Coqueret, Guillaume, et al.
Pubblicazione: (2025)

A duality framework for analyzing random feature and two-layer neural networks
di: Chen, Hongrui, et al.
Pubblicazione: (2023)

Sampling, Diffusions, and Stochastic Localization
di: Montanari, Andrea
Pubblicazione: (2023)

Quantitative convergence of trained single layer neural networks to Gaussian processes
di: Mosig, Eloy, et al.
Pubblicazione: (2025)

The Lattice Overparametrization Paradigm for the Machine Learning of Lattice Operators
di: Marcondes, Diego, et al.
Pubblicazione: (2023)

On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
di: Kobialka, Julius, et al.
Pubblicazione: (2026)

On the Epistemic Uncertainty of Overparametrized Neural Networks
di: Rügamer, David
Pubblicazione: (2026)

High-dimensional logistic regression with missing data: Imputation, regularization, and universality
di: Verchand, Kabir Aladin, et al.
Pubblicazione: (2024)

Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
di: Huang, Jie, et al.
Pubblicazione: (2026)

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime
di: Barboni, Raphaël, et al.
Pubblicazione: (2025)

Understanding Overparametrization in Survival Models through Interpolation
di: Liu, Yin, et al.
Pubblicazione: (2025)

Optimization and generalization analysis for two-layer physics-informed neural networks without over-parametrization
di: Zeng, Zhihan, et al.
Pubblicazione: (2025)

CBMAP: Clustering-based manifold approximation and projection for dimensionality reduction
di: Dogan, Berat
Pubblicazione: (2024)

Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD
di: Arnaboldi, Luca, et al.
Pubblicazione: (2023)

Gaussian mixture layers for neural networks
di: Chewi, Sinho, et al.
Pubblicazione: (2025)

Interpretable non-linear dimensionality reduction using gaussian weighted linear transformation
di: Bergh, Erik
Pubblicazione: (2025)

Training Overparametrized Neural Networks in Sublinear Time
di: Deng, Yichuan, et al.
Pubblicazione: (2022)

Symmetries in Overparametrized Neural Networks: A Mean-Field View
di: Maass, Javier, et al.
Pubblicazione: (2024)

Random-projection ensemble dimension reduction
di: Zhou, Wenxing, et al.
Pubblicazione: (2024)

Simultaneous linear connectivity of neural networks modulo permutation
di: Sharma, Ekansh, et al.
Pubblicazione: (2024)

Memory capacity of two layer neural networks with smooth activations
di: Madden, Liam, et al.
Pubblicazione: (2023)

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
di: Wan, Yijun, et al.
Pubblicazione: (2023)

Lower Bounds for the Convergence of Tensor Power Iteration on Random Overcomplete Models
di: Wu, Yuchen, et al.
Pubblicazione: (2022)

Sharp Analysis of Power Iteration for Tensor PCA
di: Wu, Yuchen, et al.
Pubblicazione: (2024)

Sobolev neural network with residual weighting as a surrogate in linear and non-linear mechanics
di: Kilicsoy, A. O. M., et al.
Pubblicazione: (2024)

A universal linearized subspace refinement framework for neural networks
di: Cao, Wenbo, et al.
Pubblicazione: (2026)

Computational bottlenecks for denoising diffusions
di: Montanari, Andrea, et al.
Pubblicazione: (2025)

Any-dimensional equivariant neural networks
di: Levin, Eitan, et al.
Pubblicazione: (2023)

SIMAP: A simplicial-map layer for neural networks
di: Gonzalez-Diaz, Rocio, et al.
Pubblicazione: (2024)

Generalization error bounds for two-layer neural networks with Lipschitz loss function
di: Nguwi, Jiang Yu, et al.
Pubblicazione: (2026)

Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization
di: Kolb, Chris, et al.
Pubblicazione: (2023)

Critical Points of Degenerate Metrics on Algebraic Varieties: A Tale of Overparametrization
di: Marchetti, Giovanni Luca, et al.
Pubblicazione: (2025)

Macroscopic auxiliary asymptotic preserving neural networks for the linear radiative transfer equations
di: Li, Hongyan, et al.
Pubblicazione: (2024)

Causally Consistent Normalizing Flow
di: Zhou, Qingyang, et al.
Pubblicazione: (2024)

Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime
di: Camilli, Francesco, et al.
Pubblicazione: (2025)