Imagen de Portada

A Law of Data Reconstruction for Random Features (and Beyond)

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Iurada, Leonardo, Bombari, Simone, Tommasi, Tatiana, Mondelli, Marco
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features
por: Bombari, Simone, et al.
Publicado: (2023)

Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
por: Bombari, Simone, et al.
Publicado: (2024)

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
por: Bombari, Simone, et al.
Publicado: (2025)

Privacy for Free in the Overparameterized Regime
por: Bombari, Simone, et al.
Publicado: (2024)

Efficient Model Editing with Task-Localized Sparse Fine-tuning
por: Iurada, Leonardo, et al.
Publicado: (2025)

High-Dimensional Private Linear Regression with Optimal Rates
por: Bombari, Simone, et al.
Publicado: (2025)

Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning
por: Iurada, Leonardo, et al.
Publicado: (2024)

Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge Regression
por: Wu, Diyuan, et al.
Publicado: (2026)

Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime
por: Wu, Diyuan, et al.
Publicado: (2025)

A Second-Order Perspective on Pruning at Initialization and Knowledge Transfer
por: Iurada, Leonardo, et al.
Publicado: (2025)

Domain Randomization for Robust, Affordable and Effective Closed-loop Control of Soft Robots
por: Tiboni, Gabriele, et al.
Publicado: (2023)

High-dimensional Analysis of Synthetic Data Selection
por: Rezaei, Parham, et al.
Publicado: (2025)

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws
por: Ildiz, M. Emrullah, et al.
Publicado: (2024)

Optimal Regularization for Performative Learning
por: Cyffers, Edwige, et al.
Publicado: (2025)

DP-KAN: Differentially Private Kolmogorov-Arnold Networks
por: Kalinin, Nikita P., et al.
Publicado: (2024)

Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth
por: Kögler, Kevin, et al.
Publicado: (2024)

Domain Randomization via Entropy Maximization
por: Tiboni, Gabriele, et al.
Publicado: (2023)

Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
por: Zhang, Yihan, et al.
Publicado: (2024)

Improved Convergence of Score-Based Diffusion Models via Prediction-Correction
por: Pedrotti, Francesco, et al.
Publicado: (2023)

Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?
por: Súkeník, Peter, et al.
Publicado: (2024)

Average gradient outer product as a mechanism for deep neural collapse
por: Beaglehole, Daniel, et al.
Publicado: (2024)

Power-Law Spectrum of the Random Feature Model
por: Paquette, Elliot, et al.
Publicado: (2026)

Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
por: Súkeník, Peter, et al.
Publicado: (2025)

Precise Asymptotics for Spectral Methods in Mixed Generalized Linear Models
por: Zhang, Yihan, et al.
Publicado: (2022)

Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery
por: Kovačević, Filip, et al.
Publicado: (2025)

TAMIS: Tailored Membership Inference Attacks on Synthetic Data
por: Andrey, Paul, et al.
Publicado: (2025)

Attention with Trained Embeddings Provably Selects Important Tokens
por: Wu, Diyuan, et al.
Publicado: (2025)

Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
por: Jacot, Arthur, et al.
Publicado: (2024)

Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
por: Njaradi, Valentina, et al.
Publicado: (2026)

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning
por: Kovačević, Filip, et al.
Publicado: (2026)

Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
por: Súkeník, Peter, et al.
Publicado: (2026)

Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime
por: Hu, Hong, et al.
Publicado: (2024)

Deep Random Features for Scalable Interpolation of Spatiotemporal Data
por: Chen, Weibin, et al.
Publicado: (2024)

Privacy Amplification Through Synthetic Data: Insights from Linear Regression
por: Pierquin, Clément, et al.
Publicado: (2025)

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning
por: Wu, Xiaojun, et al.
Publicado: (2025)

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
por: Anguita, Nicolas, et al.
Publicado: (2026)

Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing
por: Zhang, Yihan, et al.
Publicado: (2023)

Optimal Estimation in Orthogonally Invariant Generalized Linear Models: Spectral Initialization and Approximate Message Passing
por: Zhang, Yihan, et al.
Publicado: (2026)

Data-Aware Random Feature Kernel for Transformers
por: Farzam, Amirhossein, et al.
Publicado: (2026)

Test-Time Training Provably Improves Transformers as In-context Learners
por: Gozeten, Halil Alperen, et al.
Publicado: (2025)