Timezone: »

OptNet: Differentiable Optimization as a Layer in Neural Networks
Brandon Amos · Zico Kolter

Wed Aug 09 01:30 AM -- 05:00 AM (PDT) @ Gallery #7

This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks. These layers encode constraints and complex dependencies between the hidden states that traditional convolutional and fully-connected layers often cannot capture. In this paper, we explore the foundations for such an architecture: we show how techniques from sensitivity analysis, bilevel optimization, and implicit differentiation can be used to exactly differentiate through these layers and with respect to layer parameters; we develop a highly efficient solver for these layers that exploits fast GPU-based batch solves within a primal-dual interior point method, and which provides backpropagation gradients with virtually no additional cost on top of the solve; and we highlight the application of these approaches in several problems. In one notable example, we show that the method is capable of learning to play mini-Sudoku (4x4) given just input and output games, with no a priori information about the rules of the game; this highlights the ability of our architecture to learn hard constraints better than other neural architectures.

Author Information

Brandon Amos (Carnegie Mellon University)
Zico Kolter (Carnegie Mellon University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors