Regularizing Neural Networks by Penalizing Confident Output Distributions

Invalid Date (modified: Nov 04, 2016) ICLR 2017 conference submission readers: everyone
  • Abstract: We propose 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. We connect our confidence penalty to label smoothing through the direction of the KL divergence between networks output distribution and the uniform distribution. We exhaustively evaluate our proposed confidence penalty and label smoothing (uniform and unigram) 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 our confidence penalty improve state-of-the-art models across benchmarks without modifying existing hyper-parameters.
  • TL;DR: 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.
  • Conflicts: google.com
  • Keywords: Deep learning, Supervised Learning, Speech, Structured prediction
0 Replies

Loading