2024/12/15 by Zeeshan Patel, Patel, Zeeshan, James DeLoye +2 · 3 citations
Computer Science · #Reinforcement Learning in Robotics
paper · pdf · doi:10.48550/arxiv.2412.11024
In this paper, we present a comprehensive theoretical comparison of diffusion and flow matching under the Generator Matching framework. Despite their apparent differences, both diffusion and flow matching can be viewed under the unified framework of Generator Matching. By recasting both diffusion and flow matching under the same generative Markov framework, we provide theoretical insights into why flow matching models can be more robust empirically and how novel model classes can be constructed by mixing deterministic and stochastic components. Our analysis offers a fresh perspective on the relationships between state-of-the-art generative modeling paradigms.