Input-Convex Deep Networks

Brandon Amos, J. Zico Kolter

Feb 18, 2016 (modified: Feb 18, 2016) ICLR 2016 workshop submission readers: everyone
  • Abstract: This paper introduces a new class of neural networks that we refer to as input-convex neural networks, networks that are convex in their inputs (as opposed to their parameters). We discuss the nature and representational power of these networks, illustrate how the prediction (inference) problem can be solved via convex optimization, and discuss their application to structured prediction problems. We highlight a few simple examples of these networks applied to classification tasks, where we illustrate that the networks perform substantially better than any other approximator we are aware of that is convex in its inputs.
  • Conflicts: