International Conference on Machine Learning · 2014 · 53 citations · 16 references
ComputingComputer ScienceMathematicsComputer VisionMachine LearningOptimizationConvex OptimizationDeep LearningImage ReconstructionNeural NetworksHalf-wave RectificationLipschitz ConditionsLipschitz ContinuityLower BoundsPooling Operations
In this work we compute lower Lipschitz bounds of lp pooling operators for p = 1, 2, ∞ as well as lp pooling operators preceded by half-rectification layers. These give sufficient conditions for the design of invertible neural network 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.
16