Search Machine Learning Repository: @inproceedings{icml2014c2_estrach14,
    Publisher = {JMLR Workshop and Conference Proceedings},
    Title = {Signal recovery from Pooling Representations},
    Url = {http://jmlr.org/proceedings/papers/v32/estrach14.pdf},
    Abstract = {Pooling operators construct non-linear representations by cascading a redundant linear transform, followed by a point-wise nonlinearity and a local aggregation, typically implemented with a $\ell_p$ norm. Their efficiency in recognition architectures is based on their ability to locally contract the input space, but also on their capacity to retain as much stable information as possible. We address this latter question by computing the upper and lower Lipschitz bounds of $\ell_p$ pooling operators for $p=1, 2, \infty$ as well as their half-rectified equivalents, which give sufficient conditions for the design of invertible pooling layers. Numerical experiments on MNIST and image patches confirm that pooling layers can be inverted with phase recovery algorithms. Moreover, the regularity of the inverse pooling, controlled by the lower Lipschitz constant, is empirically verified with a nearest neighbor regression.},
    Author = {Joan B. Estrach and Arthur Szlam and Yann Lecun},
    Editor = {Tony Jebara and Eric P. Xing},
    Year = {2014},
    Booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},
    Pages = {307-315}
   }