DeepAI AI Chat
Log In Sign Up

Regularizing Neural Networks by Penalizing Confident Output Distributions

by   Gabriel Pereyra, et al.

We systematically explore regularizing neural networks by penalizing low entropy output distributions. We show that penalizing low entropy output distributions, which has been shown to improve exploration in reinforcement learning, acts as a strong regularizer in supervised learning. Furthermore, we connect a maximum entropy based confidence penalty to label smoothing through the direction of the KL divergence. We exhaustively evaluate the proposed confidence penalty and label smoothing on 6 common benchmarks: image classification (MNIST and Cifar-10), language modeling (Penn Treebank), machine translation (WMT'14 English-to-German), and speech recognition (TIMIT and WSJ). We find that both label smoothing and the confidence penalty improve state-of-the-art models across benchmarks without modifying existing hyperparameters, suggesting the wide applicability of these regularizers.


page 1

page 2

page 3

page 4


Rethinking Label Smoothing on Multi-hop Question Answering

Label smoothing is a regularization technique widely used in supervised ...

The Implicit Length Bias of Label Smoothing on Beam Search Decoding

Label smoothing is ubiquitously applied in Neural Machine Translation (N...

Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing

Prior work has explored directly regularizing the output distributions o...

ProSelfLC: Progressive Self Label Correction for Target Revising in Label Noise

In this work, we address robust deep learning under label noise (semi-su...

Calibrating Histopathology Image Classifiers using Label Smoothing

The classification of histopathology images fundamentally differs from t...

Stabilizing Transformer Training by Preventing Attention Entropy Collapse

Training stability is of great importance to Transformers. In this work,...

Capturing Label Distribution: A Case Study in NLI

We study estimating inherent human disagreement (annotation label distri...