Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data
Read the original on arXiv Machine Learning →Bernoulli Flow Models (BFM) introduce a continuous global Bernoulli probability flow path for binary data generation, replacing sequential one‑step Markov diffusion chains. By deriving analytical closed‑form posterior transitions over arbitrary time intervals, BFM eliminates the need for approximating multi‑step likelihoods and allows inference with far fewer function evaluations while maintaining sample quality. Experiments demonstrate that a BFM trained with 256 steps achieves an FID of 9.22 on LSUN Churches 256×256 using only 16 sampling steps, outperforming state‑of‑the‑art discrete baselines and remaining competitive under full‑step inference.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.