cs.LGSep 3, 2026

Conditioning Degenerate Diffusion Models

Authors: Uğur AydınTamer Başar

Organizations: Department of Electrical and Computer Engineering and Coordinated Science Laboratory University of Illinois Urbana Champaign Illinois, IL 61801, USA

Abstract

Current conditioned generative models heavily rely on score functions for guidance during training. When the generative model is a diffusion process with a singular diffusion coefficient and the underlying (conditional) densities either do not exist or are not smooth, we use causal optimal transport to define \emph{approximate} loss functions that identify a minimum-entropy control for guidance under minimal assumptions. Our approach relies on causal optimal transport and its characterization through the predictable representation property of (conditioned) diffusion processes whose associated martingale problem is well posed, à la Üstünel.

Explore similar work

CardsList
  1. Simulation-free and finite-time diffusion model

    Aug 4, 2026Kentaro Kaba, Masayuki Ohzeki, Yuki SughiyamaConditional Distribution

  2. Towards More General Control of Diffusion Models Using Jeffrey Guidance

    Jun 11, 2026Raphaël Razafindralambo, Rémy Sun, Frédéric Precioso +2

  3. Spectral Guidance for Flexible and Efficient Control of Diffusion Models

    May 27, 2026Gabriel Moreira, Manuel Marques, João Paulo Costeira +1Generative Processes