On the Compressive Power of Boolean Threshold Autoencoders
This work addresses theoretical limitations in neural network compression for binary data, providing insights into layer-depth trade-offs, but it is incremental as it builds on existing autoencoder theory.
The paper investigates the compressive power of Boolean threshold autoencoders, showing that a seven-layer architecture can compress any set of n distinct binary vectors with a middle layer of logarithmic size, but no three-layer autoencoder achieves this, and a trade-off exists where a five-layer version works with a larger middle layer.
An autoencoder is a layered neural network whose structure can be viewed as consisting of an encoder, which compresses an input vector of dimension $D$ to a vector of low dimension $d$, and a decoder which transforms the low-dimensional vector back to the original input vector (or one that is very similar). In this paper we explore the compressive power of autoencoders that are Boolean threshold networks by studying the numbers of nodes and layers that are required to ensure that the numbers of nodes and layers that are required to ensure that each vector in a given set of distinct input binary vectors is transformed back to its original. We show that for any set of $n$ distinct vectors there exists a seven-layer autoencoder with the smallest possible middle layer, (i.e., its size is logarithmic in $n$), but that there is a set of $n$ vectors for which there is no three-layer autoencoder with a middle layer of the same size. In addition we present a kind of trade-off: if a considerably larger middle layer is permissible then a five-layer autoencoder does exist. We also study encoding by itself. The results we obtain suggest that it is the decoding that constitutes the bottleneck of autoencoding. For example, there always is a three-layer Boolean threshold encoder that compresses $n$ vectors into a dimension that is reduced to twice the logarithm of $n$.