Log In Sign Up

Label Noise SGD Provably Prefers Flat Global Minimizers

by   Alex Damian, et al.

In overparametrized models, the noise in stochastic gradient descent (SGD) implicitly regularizes the optimization trajectory and determines which local minimum SGD converges to. Motivated by empirical studies that demonstrate that training with noisy labels improves generalization, we study the implicit regularization effect of SGD with label noise. We show that SGD with label noise converges to a stationary point of a regularized loss L(θ) +λ R(θ), where L(θ) is the training loss, λ is an effective regularization parameter depending on the step size, strength of the label noise, and the batch size, and R(θ) is an explicit regularizer that penalizes sharp minimizers. Our analysis uncovers an additional regularization effect of large learning rates beyond the linear scaling rule that penalizes large eigenvalues of the Hessian more than small ones. We also prove extensions to classification with general loss functions, SGD with momentum, and SGD with general noise covariance, significantly strengthening the prior work of Blanc et al. to global convergence and large learning rates and of HaoChen et al. to general models.


page 1

page 2

page 3

page 4


What Happens after SGD Reaches Zero Loss? –A Mathematical Framework

Understanding the implicit bias of Stochastic Gradient Descent (SGD) is ...

When does SGD favor flat minima? A quantitative characterization via linear stability

The observation that stochastic gradient descent (SGD) favors flat minim...

Regularization in neural network optimization via trimmed stochastic gradient descent with noisy label

Regularization is essential for avoiding over-fitting to training data i...

Variance Reduction in Deep Learning: More Momentum is All You Need

Variance reduction (VR) techniques have contributed significantly to acc...

Inherent Noise in Gradient Based Methods

Previous work has examined the ability of larger capacity neural network...

Shape Matters: Understanding the Implicit Bias of the Noise Covariance

The noise in stochastic gradient descent (SGD) provides a crucial implic...

On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)

It is generally recognized that finite learning rate (LR), in contrast t...