Entropic gradient descent algorithms and wide flat minima

by   Fabrizio Pittorino, et al.

The properties of flat minima in the empirical risk landscape of neural networks have been debated for some time. Increasing evidence suggests they possess better generalization capabilities with respect to sharp ones. First, we discuss Gaussian mixture classification models and show analytically that there exist Bayes optimal pointwise estimators which correspond to minimizers belonging to wide flat regions. These estimators can be found by applying maximum flatness algorithms either directly on the classifier (which is norm independent) or on the differentiable loss function used in learning. Next, we extend the analysis to the deep learning scenario by extensive numerical validations. Using two algorithms, Entropy-SGD and Replicated-SGD, that explicitly include in the optimization objective a non-local flatness measure known as local entropy, we consistently improve the generalization error for common architectures (e.g. ResNet, EfficientNet). An easy to compute flatness measure shows a clear correlation with test accuracy.


page 1

page 2

page 3

page 4


Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures

We analyze the connection between minimizers with good generalizing prop...

Shaping the learning landscape in neural networks around wide flat minima

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-c...

Entropy-SGD: Biasing Gradient Descent Into Wide Valleys

This paper proposes a new optimization algorithm called Entropy-SGD for ...

Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape

In this paper, we study the sharpness of a deep learning (DL) loss lands...

Regularizing Neural Networks via Adversarial Model Perturbation

Recent research has suggested that when training neural networks, flat l...

G-TRACER: Expected Sharpness Optimization

We propose a new regularization scheme for the optimization of deep lear...

Please sign up or login with your details

Forgot password? Click here to reset