How Could Polyhedral Theory Harness Deep Learning? [article]

Thiago Serra and Christian Tjandraatmadja and Srikumar Ramalingam
2018 arXiv   pre-print
The holy grail of deep learning is to come up with an automatic method to design optimal architectures for different applications. In other words, how can we effectively dimension and organize neurons along the network layers based on the computational resources, input size, and amount of training data? We outline promising research directions based on polyhedral theory and mixed-integer representability that may offer an analytical approach to this question, in contrast to the empirical techniques often employed.
arXiv:1806.06365v1 fatcat:oj4v3ypbenfo3ljn2ft75ajiu4