Contact Wasserstein Geodesics for Non-Conservative Schrödinger Bridges
This provides a more versatile framework for modeling real-world stochastic processes in domains such as molecular dynamics and image generation, though it is an incremental advancement over prior energy-conserving methods.
The paper tackled the limitation of existing Schrödinger Bridge methods by introducing a non-conservative formulation that allows energy to vary over time, enabling modeling of richer stochastic processes like manifold navigation and image generation with near-linear computational complexity.
The Schrödinger Bridge provides a principled framework for modeling stochastic processes between distributions; however, existing methods are limited by energy-conservation assumptions, which constrains the bridge's shape preventing it from model varying-energy phenomena. To overcome this, we introduce the non-conservative generalized Schrödinger bridge (NCGSB), a novel, energy-varying reformulation based on contact Hamiltonian mechanics. By allowing energy to change over time, the NCGSB provides a broader class of real-world stochastic processes, capturing richer and more faithful intermediate dynamics. By parameterizing the Wasserstein manifold, we lift the bridge problem to a tractable geodesic computation in a finite-dimensional space. Unlike computationally expensive iterative solutions, our contact Wasserstein geodesic (CWG) is naturally implemented via a ResNet architecture and relies on a non-iterative solver with near-linear complexity. Furthermore, CWG supports guided generation by modulating a task-specific distance metric. We validate our framework on tasks including manifold navigation, molecular dynamics predictions, and image generation, demonstrating its practical benefits and versatility.