Log In Sign Up

Temperature check: theory and practice for training models with softmax-cross-entropy losses

by   Atish Agarwala, et al.

The softmax function combined with a cross-entropy loss is a principled approach to modeling probability distributions that has become ubiquitous in deep learning. The softmax function is defined by a lone hyperparameter, the temperature, that is commonly set to one or regarded as a way to tune model confidence after training; however, less is known about how the temperature impacts training dynamics or generalization performance. In this work we develop a theory of early learning for models trained with softmax-cross-entropy loss and show that the learning dynamics depend crucially on the inverse-temperature β as well as the magnitude of the logits at initialization, ||β z||_2. We follow up these analytic results with a large-scale empirical study of a variety of model architectures trained on CIFAR10, ImageNet, and IMDB sentiment analysis. We find that generalization performance depends strongly on the temperature, but only weakly on the initial logit magnitude. We provide evidence that the dependence of generalization on β is not due to changes in model confidence, but is a dynamical phenomenon. It follows that the addition of β as a tunable hyperparameter is key to maximizing model performance. Although we find the optimal β to be sensitive to the architecture, our results suggest that tuning β over the range 10^-2 to 10^1 improves performance over all architectures studied. We find that smaller β may lead to better peak performance at the cost of learning stability.


On the Rényi Cross-Entropy

The Rényi cross-entropy measure between two distributions, a generalizat...

Amended Cross Entropy Cost: Framework For Explicit Diversity Encouragement

Cross Entropy (CE) has an important role in machine learning and, in par...

Calibrating Deep Neural Networks using Focal Loss

Miscalibration – a mismatch between a model's confidence and its correct...

Fine-tune your Classifier: Finding Correlations With Temperature

Temperature is a widely used hyperparameter in various tasks involving n...

Understanding Gender and Racial Disparities in Image Recognition Models

Large scale image classification models trained on top of popular datase...

Analysis of Softmax Approximation for Deep Classifiers under Input-Dependent Label Noise

Modelling uncertainty arising from input-dependent label noise is an inc...

Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax

The Gumbel-Softmax is a continuous distribution over the simplex that is...