Domonkos Csuzdi

Domonkos Csuzdi, Tamás Bécsi, Olivér Törő

Log-homotopy particle flow filters realize nonlinear Bayesian estimation by continuously migrating samples from the prior to the posterior distribution. This transport is governed by a pseudo-time ordinary differential equation (ODE). A major practical challenge of these filters is the need for numerical integration, which suffers from high computational cost and susceptibility to stiffness. This paper develops an exact, integration-free closed-form solution for the exact Daum--Huang (EDH) deterministic particle flow under vector linear Gaussian measurements. By transforming the ODE into a specific eigenspace, closed-form algebraic expressions are derived for both the homogeneous state transition matrix and the inhomogeneous forcing term. We prove that this analytic solution is mathematically equivalent to the exact Kalman measurement update. Furthermore, we demonstrate how this closed-form evaluation can be embedded within an $N$-step slicing method, providing a stiffness-mitigating, integration-free particle update for highly nonlinear measurement models.

Olivér Törő, Domonkos Csuzdi, Tamás Bécsi

The log-homotopy particle flow filter resolves the Bayesian update by transporting particles along a continuous trajectory in pseudo-time. However, the governing partial differential equation for the flow velocity is fundamentally underdetermined, admitting an infinite family of valid solutions. In this work, we regard the particle flow as the motion of a pressureless inviscid fluid. We define a Lagrangian action based on the kinetic energy of the system, subject to the constraints imposed by the continuity equation and the log-homotopy evolution. By applying the principle of least action, we obtain the Euler--Lagrange equations for the optimal flow, which yields an irrotational potential flow structure. We show that this variational framework yields a coupled Hamilton--Jacobi equation structurally isomorphic to Madelung's hydrodynamic formulation of quantum mechanics. In this analogy, the log-homotopy constraint acts as a generalized quantum potential that generates the force required to guide the probability fluid along the exact Bayesian update path. Finally, we derive the material acceleration of the flow, shifting the formulation from a kinematic to a dynamical description. This perspective could enable the application of higher-order symplectic integrators for improved numerical stability and provide a physics-based metric for adaptive stiffness detection in high-dimensional filtering.

Domonkos Csuzdi, Tamás Bécsi, Olivér Törő

The Bayesian update step poses significant computational challenges in high-dimensional nonlinear estimation. While log-homotopy particle flow filters offer an alternative to stochastic sampling, existing formulations usually yield stiff differential equations. Conversely, existing deep learning approximations typically treat the update as a black-box task or rely on asymptotic relaxation, neglecting the exact geometric structure of the finite-horizon probability transport. In this work, we propose a physics-informed neural particle flow, which is an amortized inference framework. To construct the flow, we couple the log-homotopy trajectory of the prior to posterior density function with the continuity equation describing the density evolution. This derivation yields a governing partial differential equation (PDE), referred to as the master PDE. By embedding this PDE as a physical constraint into the loss function, we train a neural network to approximate the transport velocity field. This approach enables purely unsupervised training, eliminating the need for ground-truth posterior samples. We demonstrate that the neural parameterization acts as an implicit regularizer, mitigating the numerical stiffness inherent to analytic flows and reducing online computational complexity. Experimental validation on multimodal benchmarks and a challenging nonlinear scenario confirms better mode coverage and robustness compared to state-of-the-art baselines.

Domonkos Csuzdi, Olivér Törő, Tamás Bécsi

Particle filters are a frequent choice for inference tasks in nonlinear and non-Gaussian state-space models. They can either be used for state inference by approximating the filtering distribution or for parameter inference by approximating the marginal data (observation) likelihood. A good proposal distribution and a good resampling scheme are crucial to obtain low variance estimates. However, traditional methods like multinomial resampling introduce nondifferentiability in PF-based loss functions for parameter estimation, prohibiting gradient-based learning tasks. This work proposes a differentiable resampling scheme by deterministic sampling from an empirical cumulative distribution function. We evaluate our method on parameter inference tasks and proposal learning.