Imagen de Portada

High-dimensional Analysis of Synthetic Data Selection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rezaei, Parham, Kovacevic, Filip, Locatello, Francesco, 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

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

Towards a holistic understanding of Selection Bias for Causal Effect Identification
por: Qiu, Yiwen, 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)

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

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

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
por: Bombari, Simone, 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)

Causal Learning with the Invariance Principle
por: Montagna, Francesco, et al.
Publicado: (2026)

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

Controlling Transient Amplification Improves Long-horizon Rollouts
por: Pervez, Adeel, 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)

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

The Rate-Distortion-Polysemanticity Tradeoff in SAEs
por: Mencattini, Tommaso, et al.
Publicado: (2026)

Out-of-Distribution Detection with Relative Angles
por: Demirel, Berker, et al.
Publicado: (2024)

Navigating the Latent Space Dynamics of Neural Models
por: Fumero, Marco, et al.
Publicado: (2025)

Statistical and structural identifiability in representation learning
por: Nelson, Walter, et al.
Publicado: (2026)

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

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

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

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

A Law of Data Reconstruction for Random Features (and Beyond)
por: Iurada, Leonardo, et al.
Publicado: (2025)

Latent Functional Maps: a spectral framework for representation alignment
por: Fumero, Marco, et al.
Publicado: (2024)

Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms
por: Rezaei, Parham, et al.
Publicado: (2024)

Mechanistic PDE Networks for Discovery of Governing Equations
por: Pervez, Adeel, et al.
Publicado: (2025)

Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learning
por: Huang, Shimeng, et al.
Publicado: (2026)

Toward Identifiable Sparse Autoencoders
por: Nelson, Walter, et al.
Publicado: (2026)

Marrying Causal Representation Learning with Dynamical Systems for Science
por: Yao, Dingling, et al.
Publicado: (2024)

Learning Discrete Diffusion of Graphs via Free-Energy Gradient Flows
por: Rancati, Dario, et al.
Publicado: (2026)

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

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

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

Latent Space Translation via Inverse Relative Projection
por: Maiorca, Valentino, et al.
Publicado: (2024)

Unifying Causal Representation Learning with the Invariance Principle
por: Yao, Dingling, et al.
Publicado: (2024)

The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations
por: Yao, Dingling, et al.
Publicado: (2025)

Exploratory Causal Inference in SAEnce
por: Mencattini, Tommaso, et al.
Publicado: (2025)

Demystifying amortized causal discovery with transformers
por: Montagna, Francesco, et al.
Publicado: (2024)

Learning Pareto manifolds in high dimensions: How can regularization help?
por: Wegel, Tobias, et al.
Publicado: (2025)

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

MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging
por: Demirel, Berker, et al.
Publicado: (2025)

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