DeepDIVE: Optimizing Input-Constrained Distributions for Composite DNA Storage via Multinomial Channel

TL;DR

This paper introduces DeepDIVE, an algorithm that optimizes input distributions for DNA storage channels by combining a variational autoencoder with an advanced Blahut-Arimoto method, improving capacity under input constraints.

Contribution

It presents a novel algorithm that integrates variational autoencoders with the M-DAB algorithm to optimize input distributions for DNA storage channels.

Findings

Enhanced input distribution optimization for DNA storage.

Improved channel capacity under input constraints.

Effective integration of VAE with M-DAB algorithm.

Abstract

We address the challenge of optimizing the capacity-achieving input distribution for a multinomial channel under the constraint of limited input support size, which is a crucial aspect in the design of DNA storage systems. We propose an algorithm that further elaborates the Multidimensional Dynamic Assignment Blahut-Arimoto (M-DAB) algorithm. Our proposed algorithm integrates variational autoencoder for determining the optimal locations of input distribution, into the alternating optimization of the input distribution locations and weights.