# Separable Layers Enable Structured Efficient Linear Substitutions

arXiv: https://arxiv.org/abs/1906.00859 · HTML: https://mlsanity.com/paper/1906.00859/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 1 of 1)

- [Initialization and Regularization of Factorized Neural Layers](https://mlsanity.com/paper/2105.01029/) (2021)

## Abstract (arXiv)

In response to the development of recent efficient dense layers, this paper shows that something as simple as replacing linear components in pointwise convolutions with structured linear decompositions also produces substantial gains in the efficiency/accuracy tradeoff. Pointwise convolutions are fully connected layers and are thus prepared for replacement by structured transforms. Networks using such layers are able to learn the same tasks as those using standard convolutions, and provide Pareto-optimal benefits in efficiency/accuracy, both in terms of computation (mult-adds) and parameter count (and hence memory). Code is available at https://github.com/BayesWatch/deficient-efficient.