Constrained Variational Inference via Safe Particle Flow
For practitioners of variational inference, this provides a principled and computationally tractable way to incorporate constraints, but the results are only demonstrated on numerical simulations without concrete performance numbers.
The paper introduces a control barrier function (CBF) formulation to enforce equality and inequality constraints in variational inference, ensuring constraint satisfaction with theoretical guarantees. Numerical simulations demonstrate the method's effectiveness.
We propose a control barrier function (CBF) formulation for enforcing equality and inequality constraints in variational inference. The key idea is to define a barrier functional on the space of probability density functions that encode the desired constraints imposed on the variational density. By leveraging the Liouville equation, we establish a connection between the time derivative of the variational density and the particle drift, which enables the systematic construction of corresponding CBFs associated to the particle drift. Enforcing these CBFs gives rise to the safe particle flow and ensures that the variational density satisfies the original constraints imposed by the barrier functional. This formulation provides a principled and computationally tractable solution to constrained variational inference, with theoretical guarantees of constraint satisfaction. The effectiveness of the method is demonstrated through numerical simulations.