Lifted Schr"odinger Bridges for Gaussian Mixture Endpoints: Projection Gaps and Path-Space Obstructions
math.OC, cs.LG, cs.RO, cs.SY, eess.SY
Submitted: 2026-05-24
Updated: 2026-10-31
Comments: 37 pages; revised version of a journal submission with a new section on duality certificates
License: http://creativecommons.org/licenses/by/4.0/
The gist: We study stochastic density control between Gaussian-mixture endpoint distributions under Brownian prior dynamics.
Terminology
Abstract
We study stochastic density control between Gaussian-mixture endpoint distributions under Brownian prior dynamics. Since the direct Schrödinger bridge between Gaussian mixtures is generally not available in closed form, we introduce a lifted path-space construction in which each trajectory is augmented with a source--target component label. Consequently, the problem decomposes into Gaussian component-to-component Schrödinger bridges with explicit marginal, drift, and cost formulas, while the mixture-level assignment reduces to a finite-dimensional entropic coupling problem with a Sinkhorn scaling form. We then analyze the projection obtained by discarding or forgetting the label. By construction, the projected law satisfies the original Gaussian-mixture endpoint constraints, but its relative entropy generally differs from the lifted relative entropy by a nonnegative conditional label-information gap. This gap reveals a path-space obstruction: the lifted optimizer cannot, in general, be identified with the direct unlabeled Schrödinger bridge after projection. We also derive the posterior-averaged Markov drift associated with the projected marginal flow, prove a kinetic-energy upper bound, and identify a common path-potential condition under which the projection gap vanishes. Several numerical illustrations showing density and shape control are recorded for a self-contained exposition.
Sources
- From Schrodinger Bridge to Optimal Transport over Sub-Riemannian Manifolds
- Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control
- Flow Matching for Measure Transport and Feedback Stabilization of Control-Affine Systems
- Schr\"odinger Bridge Over A Compact Connected Lie Group
- Globally Solving Unbalanced Optimal Transport and Density Control for Gaussian Distributions
- Optimal and Diffusion Transports in Machine Learning
- Simulation-free Schr\"odinger bridges via score and flow matching
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise