An operator splitting analysis of Wasserstein--Fisher--Rao gradient flows
By: Francesca Romana Crucinio, Sahani Pathiraja
Potential Business Impact:
Makes computer learning faster by mixing two math tricks.
Wasserstein-Fisher-Rao (WFR) gradient flows have been recently proposed as a powerful sampling tool that combines the advantages of pure Wasserstein (W) and pure Fisher-Rao (FR) gradient flows. Existing algorithmic developments implicitly make use of operator splitting techniques to numerically approximate the WFR partial differential equation, whereby the W flow is evaluated over a given step size and then the FR flow (or vice versa). This works investigates the impact of the order in which the W and FR operator are evaluated and aims to provide a quantitative analysis. Somewhat surprisingly, we show that with a judicious choice of step size and operator ordering, the split scheme can converge to the target distribution faster than the exact WFR flow (in terms of model time). We obtain variational formulae describing the evolution over one time step of both sequential splitting schemes and investigate in which settings the W-FR split should be preferred to the FR-W split. As a step towards this goal we show that the WFR gradient flow preserves log-concavity and obtain the first sharp decay bound for WFR.
Similar Papers
Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flows
Methodology
Makes computers guess better by learning from examples.
Gradient Flow Sampler-based Distributionally Robust Optimization
Optimization and Control
Finds best solutions by checking worst-case scenarios.
Gradient Flow Sampler-based Distributionally Robust Optimization
Optimization and Control
Finds the best way to make smart choices.