Variance-Tilted Diffusion Models for Diverse Sampling

Iskander Azangulov, Leo Zhang, Kianoosh Ashouritaklimi

Keywords: Diffusion models, doob's h-transform, diverse sampling

TL;DR: We formulate diverse batch generation in diffusion models as exact sampling from a variance-weighted target using closed-form Doob transforms.

Abstract: Diffusion models are typically sampled independently, even when the downstream objective is to obtain a diverse set of candidates. We introduce a variance-weighted batch distribution that favors collections of samples with large empirical spread after a prescribed linear feature map. The target is specified explicitly, and the sampler is derived as the corresponding Doob $h$-transform of independent diffusion dynamics. The resulting correction has a compact form: an interaction term that repels posterior denoised means, together with a curvature term that moves particles to the region of higher feature variance. This yields an interacting-particle sampler with a transparent probabilistic target rather than a heuristic repulsive drift.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 52