Optimal Binary Autoencoding with Pairwise Correlations
This work addresses efficient binary autoencoding for machine learning applications, though it appears incremental as it builds on existing autoencoder frameworks with a specific optimization approach.
The authors tackled the problem of binary autoencoder learning by formulating it as a biconvex optimization problem that leverages pairwise correlations between encoded and decoded bits, achieving worst-case optimal loss in reconstruction with competitive experimental results.
We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits. Among all possible algorithms that use this information, ours finds the autoencoder that reconstructs its inputs with worst-case optimal loss. The optimal decoder is a single layer of artificial neurons, emerging entirely from the minimax loss minimization, and with weights learned by convex optimization. All this is reflected in competitive experimental results, demonstrating that binary autoencoding can be done efficiently by conveying information in pairwise correlations in an optimal fashion.