An Algorithm for Training Polynomial Networks

  title={An Algorithm for Training Polynomial Networks},
  author={Roi Livni and Shai Shalev-Shwartz and Ohad Shamir},
We consider deep neural networks, in which the output of each node is a quadratic function of its inputs. Similar to other deep architectures, these networks can compactly represent any function on a finite training set. The main goal of this paper is the derivation of an efficient layer-by-layer algorithm for training such networks, which we denote as the Basis Learner. The algorithm is a universal learner in the sense that the training error is guaranteed to decrease at every iteration, and… CONTINUE READING