Cover Image

A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Moniri, Behrad, Lee, Donghwan, Hassani, Hamed, Dobriban, Edgar
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
by: Moniri, Behrad, et al.
Published: (2026)

Evaluating the Performance of Large Language Models via Debates
by: Moniri, Behrad, et al.
Published: (2024)

Asymptotics of Linear Regression with Linearly Dependent Data
by: Moniri, Behrad, et al.
Published: (2024)

On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
by: Moniri, Behrad, et al.
Published: (2025)

Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models
by: Moniri, Behrad, et al.
Published: (2024)

On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
by: Zhang, Thomas T., et al.
Published: (2025)

Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity
by: Huang, Xinmeng, et al.
Published: (2023)

Provable tradeoffs in adversarially robust classification
by: Dobriban, Edgar, et al.
Published: (2020)

MultiRisk: Multiple Risk Control via Iterative Score Thresholding
by: Joshi, Sunay, et al.
Published: (2025)

Risk-Controlled Post-Processing of Decision Policies
by: Joshi, Sunay, et al.
Published: (2026)

Analysis of Off-Policy Multi-Step TD-Learning with Linear Function Approximation
by: Lee, Donghwan
Published: (2024)

Watermarking Language Models with Error Correcting Codes
by: Chao, Patrick, et al.
Published: (2024)

Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
by: Collins, Liam, et al.
Published: (2023)

One-Shot Safety Alignment for Large Language Models via Optimal Dualization
by: Huang, Xinmeng, et al.
Published: (2024)

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
by: Joshi, Sunay, et al.
Published: (2025)

A Switching System Theory of Q-Learning with Linear Function Approximation
by: Lee, Donghwan, et al.
Published: (2026)

Analysis of Off-Policy $n$-Step TD-Learning with Linear Function Approximation
by: Lim, Han-Dong, et al.
Published: (2025)

How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
by: Dandi, Yatin, et al.
Published: (2023)

Conformal Information Pursuit for Interactively Guiding Large Language Models
by: Chan, Kwan Ho Ryan, et al.
Published: (2025)

Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure
by: Demir, Samet, et al.
Published: (2025)

Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
by: Kunin, Daniel, et al.
Published: (2025)

Jailbreaking Black Box Large Language Models in Twenty Queries
by: Chao, Patrick, et al.
Published: (2023)

Lyapunov-Certified Direct Switching Theory for Q-Learning
by: Lee, Donghwan
Published: (2026)

Statistical Methods in Generative AI
by: Dobriban, Edgar
Published: (2025)

Conformal Prediction with Learned Features
by: Kiyani, Shayan, et al.
Published: (2024)

Solving a Research Problem in Mathematical Statistics with AI Assistance
by: Dobriban, Edgar
Published: (2025)

Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
by: Pang, Tianyu, et al.
Published: (2026)

R-GTD: A Geometric Analysis of Gradient Temporal-Difference Learning in Singular Regimes
by: Na, Hyunjun, et al.
Published: (2026)

How Does Gradient Descent Learn Features -- A Local Analysis for Regularized Two-Layer Neural Networks
by: Zhou, Mo, et al.
Published: (2024)

Uncertainty in Language Models: Assessment through Rank-Calibration
by: Huang, Xinmeng, et al.
Published: (2024)

Optimal Decision-Making Based on Prediction Sets
by: Wang, Tao, et al.
Published: (2026)

Fair Classification by Direct Intervention on Operating Characteristics
by: Jiang, Kevin, et al.
Published: (2025)

Deep Q-Learning with Gradient Target Tracking
by: Park, Bum Geun, et al.
Published: (2025)

Soft Deterministic Policy Gradient with Gaussian Smoothing
by: Na, Hyunjun, et al.
Published: (2026)

Taming the Adversary: Stable Minimax Deep Deterministic Policy Gradient via Fractional Objectives
by: Lee, Taeho, et al.
Published: (2026)

Minimax Statistical Estimation under Wasserstein Contamination
by: Chao, Patrick, et al.
Published: (2023)

New Versions of Gradient Temporal Difference Learning
by: Lee, Donghwan, et al.
Published: (2021)

Bayes-Optimal Fair Classification with Linear Disparity Constraints via Pre-, In-, and Post-processing
by: Zeng, Xianli, et al.
Published: (2024)

SymmPI: Predictive Inference for Data with Group Symmetries
by: Dobriban, Edgar, et al.
Published: (2023)

Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
by: Nichani, Eshaan, et al.
Published: (2023)