Invertible Low-Divergence Coding

Several applications in communication, control, and learning require approximating target distributions to within small informational divergence. The additional requirement of invertibility usually leads using encoders that are one-to-one mappings, also known as distribution matchers. However, even the best have divergences grow logarithmically with block length. To overcome this limitation, an encoder is proposed has invertible one-to-many mapping a low-rate random number generator (RNG). Two algorithms developed design by assigning strings either most-likely first or least-likely order. Both give information rates approaching entropy exponentially decreasing divergence vanishing RNG rate