paper-with-me

Papers

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

2022-02-15 · Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett

In this work, we provide a characterization of the feature-learning process in two-layer ReLU networks trained by gradient descent on the logistic loss following random initialization. We consider data with binary labels that are generated by an XOR-like function of the input features. We permit a constant fraction of the training labels to be corrupted by an adversary. We show that, although linear classifiers are no better than random guessing for the distribution we consider, two-layer ReLU networks trained by gradient descent achieve generalization error close to the label noise rate. We develop a novel proof technique that shows that at initialization, the vast majority of neurons function as random features that are only weakly correlated with useful features, and the gradient descent dynamics 'amplify' these weak, random features to strong, useful features.

📄 PDF Abstract BibTeX arXiv:2202.07626

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Feature-Wise Bias Amplification

2018-12-21 · ICLR 2019 5 · Klas Leino, Emily Black, Matt Fredrikson, Shayak Sen 외

We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth. We demonstrate that bias amplification c…

feature selectionInductive Bias

Leveraging Randomness in Model and Data Partitioning for Privacy Amplification

2025-03-04 · Andy Dong, Wei-Ning Chen, Ayfer Ozgur

We study how inherent randomness in the training process -- where each sample (or client in federated learning) contributes only to a randomly selected portion of training -- can be leveraged for privacy amplification. T…

Federated Learning

Generalizing GNNs with Tokenized Mixture of Experts

2026-02-09 · Xiaoguang Guo, Zehong Wang, Jiazheng Li, Shawn Spitzel 외 arxiv

Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize under distribution shifts, and remain stable to perturbations. We show that static inference induces a fundamental tradeo…

An Effective Theory of Bias Amplification

2024-10-07 · Arjun Subramonian, Samuel J. Bell, Levent Sagun, Elvis Dohmatob

Machine learning models can capture and amplify biases present in data, leading to disparate test performance across social groups. To better understand, evaluate, and mitigate these biases, a deeper theoretical understa…

Privacy Amplification via Random Check-Ins

2020-07-13 · NeurIPS 2020 12 · Borja Balle, Peter Kairouz, H. Brendan McMahan, Om Thakkar 외

Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fundamental building block in many applications for learning over sensitive data. Two standard approaches, privacy amplification by subsampling, and pri…

Federated Learning