Imagen de Portada

How Does Overparameterization Affect Features?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Duzgun, Ahmet Cagri, Jelassi, Samy, Li, Yuanzhi
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How Does Overparameterization Affect Machine Unlearning of Deep Neural Networks?
por: Alon, Gal, et al.
Publicado: (2025)

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks
por: Prabhakar, Akshara, et al.
Publicado: (2024)

Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models
por: Jelassi, Samy, et al.
Publicado: (2026)

Collective Model Intelligence Requires Compatible Specialization
por: Pari, Jyothish, et al.
Publicado: (2024)

How Does Quantization Affect Multilingual LLMs?
por: Marchisio, Kelly, et al.
Publicado: (2024)

To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning
por: Qin, Tian, et al.
Publicado: (2025)

Universal Length Generalization with Turing Programs
por: Hou, Kaiying, et al.
Publicado: (2024)

Q-Probe: A Lightweight Approach to Reward Maximization for Language Models
por: Li, Kenneth, et al.
Publicado: (2024)

Repeat After Me: Transformers are Better than State Space Models at Copying
por: Jelassi, Samy, et al.
Publicado: (2024)

Mixture of Parrots: Experts improve memorization more than reasoning
por: Jelassi, Samy, et al.
Publicado: (2024)

The Recurrent Transformer: Greater Effective Depth and Efficient Decoding
por: Oncescu, Costin-Andrei, et al.
Publicado: (2026)

Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
por: Li, Binghui, et al.
Publicado: (2024)

Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones
por: Mirtaheri, Parsa, et al.
Publicado: (2025)

The Role of Sparsity for Length Generalization in Transformers
por: Golowich, Noah, et al.
Publicado: (2025)

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
por: Zhao, Rosie, et al.
Publicado: (2025)

Theoretical Limitations of Ensembles in the Age of Overparameterization
por: Dern, Niclas, et al.
Publicado: (2024)

The Interpolating Information Criterion for Overparameterized Models
por: Hodgkinson, Liam, et al.
Publicado: (2023)

How Much Training Data is Memorized in Overparameterized Autoencoders? An Inverse Problem Perspective on Memorization Evaluation
por: Abitbul, Koren, et al.
Publicado: (2023)

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

Machine Unlearning under Overparameterization
por: Block, Jacob L., et al.
Publicado: (2025)

How Does Code Pretraining Affect Language Model Task Performance?
por: Petty, Jackson, et al.
Publicado: (2024)

How Does Response Length Affect Long-Form Factuality
por: Zhao, James Xu, et al.
Publicado: (2025)

The Role of Symmetry in Optimizing Overparameterized Networks
por: Sareen, Kusha, et al.
Publicado: (2026)

Provable Generalization in Overparameterized Neural Nets
por: Dhingra, Aviral
Publicado: (2025)

Overparameterized Multiple Linear Regression as Hyper-Curve Fitting
por: Atza, E., et al.
Publicado: (2024)

Dual Space Preconditioning for Gradient Descent in the Overparameterized Regime
por: Ghane, Reza, et al.
Publicado: (2026)

An Analytical Model for Overparameterized Learning Under Class Imbalance
por: Mor, Eliav, et al.
Publicado: (2025)

A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data & Overparameterization?
por: Xiao, Tim Z., et al.
Publicado: (2023)

On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
por: Li, Binghui, et al.
Publicado: (2023)

On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
por: Wei, Yudong, et al.
Publicado: (2025)

How Does Preconditioning Guide Feature Learning in Deep Neural Networks?
por: Yoshida, Kotaro, et al.
Publicado: (2025)

Critical Influence of Overparameterization on Sharpness-aware Minimization
por: Shin, Sungbin, et al.
Publicado: (2023)

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
por: Zhang, Yaoyu, et al.
Publicado: (2024)

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
por: Wu, Jingfeng, et al.
Publicado: (2025)

Task Shift: From Classification to Regression in Overparameterized Linear Models
por: LaBonte, Tyler, et al.
Publicado: (2025)

Estimation of Toeplitz Covariance Matrices using Overparameterized Gradient Descent
por: Busbib, Daniel, et al.
Publicado: (2025)

Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models
por: Wu, David X., et al.
Publicado: (2023)

Bayesian Inference for Consistent Predictions in Overparameterized Nonlinear Regression
por: Wakayama, Tomoya
Publicado: (2024)

Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality
por: Zhang, Ruijia, et al.
Publicado: (2025)

Overparameterization of deep ResNet: zero loss and mean-field analysis
por: Ding, Zhiyan, et al.
Publicado: (2021)