We present a new method for making diffusion models faster to sample.

Neural Information Processing Systems http://nips.cc/

Themodelhastodetermine the label yk of the query input by applying the nearest neighbor algorithm in its forward pass (Figure 1c). This task subsumes various associative recall tasks considered in earlier works (cf.

Inspired by a first-order optimization method called mirror descent, this paper proposes topredict asequence ofrewardfunctions, which areiterativesolutions for a constrained convex problem. IRL solutions derived by mirror descent are tolerant totheuncertainty incurred bytargetdensity estimation sincetheamount of reward learning is regulated with respect to local geometric constraints.