Image de couverture de livre

High-dimensional Analysis of Synthetic Data Selection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Rezaei, Parham, Kovacevic, Filip, Locatello, Francesco, Mondelli, Marco
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery
par: Kovačević, Filip, et autres
Publié: (2025)

Towards a holistic understanding of Selection Bias for Causal Effect Identification
par: Qiu, Yiwen, et autres
Publié: (2026)

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning
par: Kovačević, Filip, et autres
Publié: (2026)

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
par: Anguita, Nicolas, et autres
Publié: (2026)

How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features
par: Bombari, Simone, et autres
Publié: (2023)

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
par: Bombari, Simone, et autres
Publié: (2025)

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

Causal Learning with the Invariance Principle
par: Montagna, Francesco, et autres
Publié: (2026)

Improved Convergence of Score-Based Diffusion Models via Prediction-Correction
par: Pedrotti, Francesco, et autres
Publié: (2023)

Controlling Transient Amplification Improves Long-horizon Rollouts
par: Pervez, Adeel, et autres
Publié: (2026)

Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime
par: Wu, Diyuan, et autres
Publié: (2025)

Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
par: Njaradi, Valentina, et autres
Publié: (2026)

The Rate-Distortion-Polysemanticity Tradeoff in SAEs
par: Mencattini, Tommaso, et autres
Publié: (2026)

Out-of-Distribution Detection with Relative Angles
par: Demirel, Berker, et autres
Publié: (2024)

Navigating the Latent Space Dynamics of Neural Models
par: Fumero, Marco, et autres
Publié: (2025)

Statistical and structural identifiability in representation learning
par: Nelson, Walter, et autres
Publié: (2026)

Privacy for Free in the Overparameterized Regime
par: Bombari, Simone, et autres
Publié: (2024)

Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
par: Bombari, Simone, et autres
Publié: (2024)

Attention with Trained Embeddings Provably Selects Important Tokens
par: Wu, Diyuan, et autres
Publié: (2025)

High-Dimensional Private Linear Regression with Optimal Rates
par: Bombari, Simone, et autres
Publié: (2025)

A Law of Data Reconstruction for Random Features (and Beyond)
par: Iurada, Leonardo, et autres
Publié: (2025)

Latent Functional Maps: a spectral framework for representation alignment
par: Fumero, Marco, et autres
Publié: (2024)

Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms
par: Rezaei, Parham, et autres
Publié: (2024)

Mechanistic PDE Networks for Discovery of Governing Equations
par: Pervez, Adeel, et autres
Publié: (2025)

Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learning
par: Huang, Shimeng, et autres
Publié: (2026)

Toward Identifiable Sparse Autoencoders
par: Nelson, Walter, et autres
Publié: (2026)

Marrying Causal Representation Learning with Dynamical Systems for Science
par: Yao, Dingling, et autres
Publié: (2024)

Learning Discrete Diffusion of Graphs via Free-Energy Gradient Flows
par: Rancati, Dario, et autres
Publié: (2026)

Optimal Regularization for Performative Learning
par: Cyffers, Edwige, et autres
Publié: (2025)

Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth
par: Kögler, Kevin, et autres
Publié: (2024)

Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
par: Zhang, Yihan, et autres
Publié: (2024)

Latent Space Translation via Inverse Relative Projection
par: Maiorca, Valentino, et autres
Publié: (2024)

Unifying Causal Representation Learning with the Invariance Principle
par: Yao, Dingling, et autres
Publié: (2024)

The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations
par: Yao, Dingling, et autres
Publié: (2025)

Exploratory Causal Inference in SAEnce
par: Mencattini, Tommaso, et autres
Publié: (2025)

Demystifying amortized causal discovery with transformers
par: Montagna, Francesco, et autres
Publié: (2024)

Learning Pareto manifolds in high dimensions: How can regularization help?
par: Wegel, Tobias, et autres
Publié: (2025)

Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?
par: Súkeník, Peter, et autres
Publié: (2024)

MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging
par: Demirel, Berker, et autres
Publié: (2025)

Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge Regression
par: Wu, Diyuan, et autres
Publié: (2026)