most citedAmbient Diffusion: Learning Clean Distributions from Corrupted Data

10 citations · 10 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2023★ 10 cited

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

Giannis Daras, Kulin Shah, Yuval Dagan +3

We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where acce…