paper-with-me

홈 › Papers

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks

2019-03-27 · Mingchen Li, Mahdi Soltanolkotabi, Samet Oymak

Modern neural networks are typically trained in an over-parameterized regime where the parameters of the model far exceed the size of the training data. Such neural networks in principle have the capacity to (over)fit any set of labels including pure noise. Despite this, somewhat paradoxically, neural network models trained via first-order methods continue to predict well on yet unseen test data. This paper takes a step towards demystifying this phenomena. Under a rich dataset model, we show that gradient descent is provably robust to noise/corruption on a constant fraction of the labels despite overparameterization. In particular, we prove that: (i) In the first few iterations where the updates are still in the vicinity of the initialization gradient descent only fits to the correct labels essentially ignoring the noisy labels. (ii) to start to overfit to the noisy labels network must stray rather far from from the initialization which can only occur after many more iterations. Together, these results show that gradient descent with early stopping is provably robust to label noise and shed light on the empirical robustness of deep networks as well as commonly adopted heuristics to prevent overfitting.

📄 PDF Abstract BibTeX arXiv:1903.11680

Code (1)

BSAraujo/machine-learning tf

Methods 이 논문이 사용한 방법론

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…

Similar Papers 제목 키워드 기반

Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond

2023-01-31 · Meyer Scetbon, Elvis Dohmatob

In this work we study the robustness to adversarial attacks, of early-stopping strategies on gradient-descent (GD) methods for linear regression. More precisely, we show that early-stopped GD is optimally robust (up to a…

regression

GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling

2025-08-26 · Arash Jamshidi, Lauri Seppäläinen, Katsiaryna Haitsiukevich, Hoang Phuc Hau Luu 외 arxiv

Machine learning models are often learned by minimising a loss function on the training data using a gradient descent algorithm. These models often suffer from overfitting, leading to a decline in predictive performance …

Transfer Learning

Implicit Sparse Regularization: The Impact of Depth and Early Stopping

2021-08-12 · NeurIPS 2021 12 · Jiangyuan Li, Thanh V. Nguyen, Chinmay Hegde, Raymond K. W. Wong

In this paper, we study the implicit bias of gradient descent for sparse regression. We extend results on regression with quadratic parametrization, which amounts to depth-2 diagonal linear networks, to more general dept…

regression

Adaptive Stopping Rule for Kernel-based Gradient Descent Algorithms

2020-01-09 · Xiangyu Chang, Shao-Bo Lin

In this paper, we propose an adaptive stopping rule for kernel-based gradient descent (KGD) algorithms. We introduce the empirical effective dimension to quantify the increments of iterations in KGD and derive an impleme…

Learning Theory

Learning Rate Annealing Can Provably Help Generalization, Even for Convex Problems

2020-05-15 · Preetum Nakkiran

Learning rate schedule can significantly affect generalization performance in modern neural networks, but the reasons for this are not yet understood. Li-Wei-Ma (2019) recently proved this behavior can exist in a simplif…

regression