@inproceedings{fb40cb8cab1e460a9d917bff0e40d699,
title = "Regularized estimation of image statistics by Score Matching",
abstract = "Score Matching is a recently-proposed criterion for training high-dimensional density models for which maximum likelihood training is intractable. It has been applied to learning natural image statistics but has so-far been limited to simple models due to the difficulty of differentiating the loss with respect to the model parameters. We show how this differentiation can be automated with an extended version of the double-backpropagation algorithm. In addition, we introduce a regularization term for the Score Matching loss that enables its use for a broader range of problem by suppressing instabilities that occur with finite training sample sizes and quantized input values. Results are reported for image denoising and super-resolution.",
author = "Kingma, {Diederik P.} and Yann LeCun",
year = "2010",
language = "English (US)",
isbn = "9781617823800",
series = "Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010",
publisher = "Neural Information Processing Systems",
booktitle = "Advances in Neural Information Processing Systems 23",
note = "24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010 ; Conference date: 06-12-2010 Through 09-12-2010",
}