Towards Robust, Locally Linear Deep Networks

Abstract

Deep networks realize complex mappings that are often understood by their locally linear behavior at or around points of interest. For example, we use the derivative of the mapping with respect to its inputs for sensitivity analysis, or to explain (obtain coordinate relevance for) a prediction. One key challenge is that such derivatives are themselves inherently unstable. In this paper, we propose a new learning problem to encourage deep networks to have stable derivatives over larger regions. While the problem is challenging in general, we focus on networks with piecewise linear activation functions. Our algorithm consists of an inference step that identifies a region around a point where linear approximation is provably stable, and an optimization step to expand such regions. We propose a novel relaxation to scale the algorithm to realistic models. We illustrate our method with residual and recurrent networks on image and sequence datasets.

Published in International Conference on Learning Representations (ICLR), 2019

References in corpus (8)

• Striving for Simplicity: The All Convolutional Net
• On the Convergence of Adam and Beyond
• SmoothGrad: removing noise by adding noise
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• An approach to reachability analysis for feed-forward ReLU neural networks
• Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
• Deep Neural Networks as 0-1 Mixed Integer Linear Programs: A Feasibility Study
• A Generative Process for Sampling Contractive Auto-Encoders