Discrete Wasserstein Flows for One-Step Generative Modeling
Quick summary
arXiv:2610.01355v1 Announce Type: cross Abstract: We introduce a new framework for one-step generative modelling on finite state spaces. To extend drifting beyond continuous domains, we use discrete Wasserstein geometry to define a target-relative KL gradient flow over the transitions of a reversible Markov kernel. We realize this probability flow at the particle level through Markov jumps and amortize the resulting transport updates into a latent-conditioned generator, so that the iterative dynamics are required only during training while inference remains one-step. In a controlled setting wh
Key takeaways
- arXiv:2610.01355v1 Announce Type: cross Abstract: We introduce a new framework for one-step generative modelling on finite state spaces.
- To extend drifting beyond continuous domains, we use discrete Wasserstein geometry to define a target-relative KL gradient flow over the transitions of a reversible Markov kernel.
- We realize this probability flow at the particle level through Markov jumps and amortize the resulting transport updates into a latent-conditioned generator, so that the iterative dynamics are required only during training while inference remains one-step.
Why it matters
The importance of “Discrete Wasserstein Flows for One-Step Generative Modeling” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments