Gauge Flow Models
This work addresses the need for more efficient generative models in machine learning, though it appears incremental as it builds on existing flow model frameworks.
The paper tackles the problem of improving generative flow models by introducing Gauge Flow Models, which incorporate a learnable Gauge Field into the flow ODE, resulting in significantly better performance on Gaussian Mixture Models compared to traditional flow models of similar or larger size.
This paper introduces Gauge Flow Models, a novel class of Generative Flow Models. These models incorporate a learnable Gauge Field within the Flow Ordinary Differential Equation (ODE). A comprehensive mathematical framework for these models, detailing their construction and properties, is provided. Experiments using Flow Matching on Gaussian Mixture Models demonstrate that Gauge Flow Models yields significantly better performance than traditional Flow Models of comparable or even larger size. Additionally, unpublished research indicates a potential for enhanced performance across a broader range of generative tasks.