AI RESEARCH

Theoretical Analysis of Engression and Reverse Markov Engression

arXiv CS.LG

ArXi:2606.01002v1 Announce Type: cross Engression is a recently proposed and effective framework for conditional distribution learning. Its multi-step Reverse Marko extension further improves generative flexibility by decomposing complex conditional sampling into sequential reverse transitions. Despite their strong empirical performance, rigorous finite-sample statistical guarantees for these methods remain unavailable.