Imagen de Portada

Weak-to-Strong Generalization Even in Random Feature Networks, Provably

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Medvedev, Marko, Lyu, Kaifeng, Yu, Dingli, Arora, Sanjeev, Li, Zhiyuan, Srebro, Nathan
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

Shift is Good: Mismatched Data Mixing Improves Test Performance
por: Medvedev, Marko, et al.
Publicado: (2025)

Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality
por: Medvedev, Marko, et al.
Publicado: (2024)

Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
por: Lyu, Kaifeng, et al.
Publicado: (2024)

Positive Distribution Shift as a Framework for Understanding Tractable Learning
por: Medvedev, Marko, et al.
Publicado: (2026)

On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
por: Malladi, Sadhika, et al.
Publicado: (2022)

Recursive Models for Long-Horizon Reasoning
por: Yang, Chenxiao, et al.
Publicado: (2026)

From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
por: Oh, Junsoo, et al.
Publicado: (2025)

AI-Assisted Generation of Difficult Math Questions
por: Shah, Vedant, et al.
Publicado: (2024)

A Quadratic Synchronization Rule for Distributed Deep Learning
por: Gu, Xinran, et al.
Publicado: (2023)

Provable Weak-to-Strong Generalization via Benign Overfitting
por: Wu, David X., et al.
Publicado: (2024)

Provable Tempered Overfitting of Minimal Nets and Typical Nets
por: Harel, Itamar, et al.
Publicado: (2024)

Can Models Learn Skill Composition from Examples?
por: Zhao, Haoyu, et al.
Publicado: (2024)

Noisy Interpolation Learning with Shallow Univariate ReLU Networks
por: Joshi, Nirmit, et al.
Publicado: (2023)

Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification
por: Zhu, Xiaohan, et al.
Publicado: (2025)

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
por: Lyu, Kaifeng, et al.
Publicado: (2023)

Provable unlearning in topic modeling and downstream tasks
por: Wei, Stanley, et al.
Publicado: (2024)

PENCIL: Long Thoughts with Short Memory
por: Yang, Chenxiao, et al.
Publicado: (2025)

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
por: Park, Simon, et al.
Publicado: (2025)

Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
por: Li, Binghui, et al.
Publicado: (2024)

How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
por: Buzaglo, Gon, et al.
Publicado: (2024)

Overfitting and Generalizing with (PAC) Bayesian Prediction in Noisy Binary Classification
por: Zhu, Xiaohan, et al.
Publicado: (2026)

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

The Price of Implicit Bias in Adversarially Robust Generalization
por: Tsilivis, Nikolaos, et al.
Publicado: (2024)

Strong and Weak Random Walks on Signed Networks
por: Babul, Shazia'Ayn, et al.
Publicado: (2024)

Depth Separation in Norm-Bounded Infinite-Width Neural Networks
por: Parkinson, Suzanna, et al.
Publicado: (2024)

Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes
por: Harel, Itamar, et al.
Publicado: (2025)

On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
por: Joshi, Nirmit, et al.
Publicado: (2024)

Tight Bounds on the Binomial CDF, and the Minimum of i.i.d Binomials, in terms of KL-Divergence
por: Zhu, Xiaohan, et al.
Publicado: (2025)

The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
por: Awano, Ryoya, et al.
Publicado: (2026)

Provable Benefits of Sinusoidal Activation for Modular Addition
por: Huang, Tianlong, et al.
Publicado: (2025)

Research Program: Theory of Learning in Dynamical Systems
por: Hazan, Elad, et al.
Publicado: (2025)

The Marginal Value of Momentum for Small Learning Rate SGD
por: Wang, Runzhe, et al.
Publicado: (2023)

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
por: Zhou, Lijia, et al.
Publicado: (2023)

On the Hardness of Learning Regular Expressions
por: Attias, Idan, et al.
Publicado: (2025)

Learning single-index models via harmonic decomposition
por: Joshi, Nirmit, et al.
Publicado: (2025)

Mixture of Weak & Strong Experts on Graphs
por: Zeng, Hanqing, et al.
Publicado: (2023)

Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
por: Li, Xinghan, et al.
Publicado: (2025)

On Weak-to-Strong Generalization and f-Divergence
por: Yao, Wei, et al.
Publicado: (2025)

Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)
por: Geng, Scott, et al.
Publicado: (2026)

A Theory of Learning with Autoregressive Chain of Thought
por: Joshi, Nirmit, et al.
Publicado: (2025)