Estimates log-likelihood of interacting particle systems using virtual particles.
problem Inconsistent estimation of finite-particle log-likelihood in large particle systems.
method Stochastic gradient estimate using continuous trajectory and virtual particle systems.
result Convergence to stationary points of limiting mean-field system's log-likelihood.
New algorithm trains latent diffusion models using interacting particles.
problem Training latent diffusion models efficiently and accurately.
method Reformulate training as minimizing a free energy functional, then approximate with interacting particles.
result The new algorithm outperforms previous methods in experiments.
Interacting particle methods are increasingly used to sample from complex and high-dimensional distributions. These stochastic particle integration techniques can be interpreted as an universal acceptance-rejection sequential particle sampler equipped with adaptive and interacting recycling mechanisms. Practically, the…
Unified approach unites GANs and diffusion models using particle methods.
problem Combining GANs and diffusion models for generative tasks.
method Proposes a unified framework where generator training is seen as a generalization of particle models.
result Demonstrates that GANs and diffusion models can be integrated within a unified framework.
Particle MCMC involves using a particle filter within an MCMC algorithm. For inference of a model which involves an unobserved stochastic process, the standard implementation uses the particle filter to propose new values for the stochastic process, and MCMC moves to propose new values for the parameters. We show how p…
Differentiable resampling improves particle filter performance.
problem Non-differentiability of traditional resampling in particle filters.
method Introduced a neural network resampler (particle transformer) trained with a likelihood-based loss function.
result Learned resampling outperforms traditional methods on synthetic and real-world tasks.
Jointly estimates flow fields and particle properties from Lagrangian data.
problem Estimating flow fields and particle properties from sparse, noisy Lagrangian data.
method Data assimilation framework coupling Eulerian and Lagrangian models.
result Joint estimation of flow fields and particle properties in various flow regimes.
The excluded area between a pair of two-dimensional hard particles with given relative orientation is the region in which one particle cannot be located due to the presence of the other particle. The magnitude of the excluded area as a function of the relative particle orientation plays a major role in the determinatio…
dSMC improves parallel processing of state-space models.
problem Processing multiple observations efficiently in state-space models.
method A parallel-in-time particle smoother that reduces complexity to log(T).
result dSMC achieves O(log(T)) time complexity on parallel architectures.
Paper uses averaging from many particle filters to approximate posterior predictive distributions.
problem Approximating posterior predictive distributions efficiently and accurately.
method Particle swarm filter algorithm that averages many particle filter approximations.
result Law of large numbers and central limit theorem support the method's effectiveness.
New method learns latent energy models using particle algorithms.
problem Learning latent variable models with energy priors.
method Continuous-time SDEs for MMLE, particle-based discretization.
result Practical algorithm converges to solve MMLE problem.
The present paper describes a practical example in which the probability distribution of the prices of a stock market blue chip is calculated as the wave function of a quantum particle confined in a potential well. This model may naturally explain the operation of several empirical rules used by technical analysts. Mod…
Enhances particle filters with neural augmentation for multi-sub-state tracking.
problem Particle filters struggle with complex or approximated models and low latency requirements.
method Learning Flock (LF) uses a neural network to correct particle weights based on sub-particle relationships.
result LF improves performance, robustness, and latency in radar multi-target tracking.
The paper studies how test particles' mass and charge vary in Kaluza-Klein models.
problem Understanding how test particles' mass and charge change in Kaluza-Klein models.
method Analyzes geodesic motion in a 5D Kaluza-Klein spacetime with background metrics encoding 4D gauge fields and Higgs-like scalars.
result The mass and charge of test particles become variable when traversing regions with massive gauge fields or non-constant Higgs scalars.
CPS solves inverse problems using forward passes and constrained particle seeking.
problem Solving inverse problems with limited forward observation information.
method Gradient-free approach that reformulates inverse problem as constrained optimization.
result CPS achieves results comparable to gradient-based methods while outperforming alternatives.
Real-life control tasks involve matters of various substances---rigid or soft bodies, liquid, gas---each with distinct physical behaviors. This poses challenges to traditional rigid-body physics engines. Particle-based simulators have been developed to model the dynamics of these complex scenes; however, relying on app…
New method for online learning in interacting particle systems.
problem Parameter estimation in stochastic interacting particle systems.
method Stochastic approximation of gradient of asymptotic log likelihood using continuous observations.
result Convergence to stationary points of asymptotic log-likelihood under suitable assumptions.
A new particle algorithm improves mean-field variational inference.
problem Efficiently approximating nonparametric posterior distributions in machine learning.
method Introduces PArticle VI (PAVI), a novel particle-based algorithm for nonparametric mean-field approximation.
result Obtains non-asymptotic error bounds for PArticle VI, providing the first end-to-end guarantee for particle-based MFVI.
Paper studies particle method for LSV model calibration, proving convergence and error bounds.
problem Calibration of local-stochastic volatility models with open well-posedness question.
method Regularized Euler--Maruyama scheme for particle approximation of McKean--Vlasov dynamics.
result Strong convergence of the Euler--Maruyama scheme with rate 1/2 in step-size.
Particle filtering is a powerful approach to sequential state estimation and finds application in many domains, including robot localization, object tracking, etc. To apply particle filtering in practice, a critical challenge is to construct probabilistic system models, especially for systems with complex dynamics or r…
A new particle filter uses diffusion models to improve state estimation from noisy data.
problem Sequentially estimating the state of a dynamical system from noisy and incomplete observations.
method Uses a diffusion model to simulate and predict system dynamics, incorporating noisy observations to refine predicted states.
result An unbiased particle filtering method that rigorously fuses observational data with diffusion model simulations.
MPM-ParVI uses particle sampling for variational inference.
problem Variational inference for complex probabilistic models.
method Material Point Method (MPM) for particle-based simulation.
result Deterministic sampling and inference for intractable densities.
SPH-ParVI uses fluid dynamics to sample unknown densities efficiently.
problem Sampling partially known densities or using gradients in probabilistic models.
method Smoothed Particle Hydrodynamics (SPH) for modeling fluid dynamics to approximate target densities.
result SPH-ParVI provides fast, flexible, scalable, and deterministic sampling for Bayesian inference and generative models.
PDDS samples from unnormalized densities using iterative particle scheme.
problem Sampling from unnormalized probability densities.
method Iterative particle scheme with novel score matching loss.
result Asymptotically consistent estimates for multimodal and high-dimensional tasks.
State space models (SSMs) provide a flexible framework for modeling complex time series via a latent stochastic process. Inference for nonlinear, non-Gaussian SSMs is often tackled with particle methods that do not scale well to long time series. The challenge is two-fold: not only do computations scale linearly with t…
New methods combine MALA and mGRAD for scalable Bayesian inference in high-dimensional state-space models.
problem Bayesian inference in high-dimensional state-space models with limited scalability.
method Combines gradient-based MALA and prior-informed mGRAD for scalable inference.
result Extends classical MCMC methods to handle multiple time steps and particles.
Improved particle-flow event reconstruction for future colliders using scalable neural networks.
problem Efficient and accurate particle reconstruction in future particle detectors.
method Comparative study of scalable machine learning models (graph neural network and kernel-based transformer) for event reconstruction.
result Graph neural network model improves jet transverse momentum resolution by up to 50%.
CMS uses machine learning to improve particle flow reconstruction.
problem Improving particle flow reconstruction in CMS.
method Machine learning, graph neural network, heterogeneous computing.
result Machine-learned PF model outperforms standard algorithm.
GER learns particle dynamics from unpaired snapshots using physics-informed GANs.
problem Learning particle dynamics from unpaired snapshots with physics constraints.
method Physics-informed generative model to fit particle ensemble distributions.
result Inferred dynamics of particle ensembles governed by SODEs up to 100 dimensions.
We consider the combined use of resampling and partial rejection control in sequential Monte Carlo methods, also known as particle filters. While the variance reducing properties of rejection control are known, there has not been (to the best of our knowledge) any work on unbiased estimation of the marginal likelihood …
We study the existence of closed trajectories of a particle model on null curves in anti-de Sitter 3-space defined by a functional which is linear in the curvature of the particle path. Explicit expressions for the trajectories are found and the existence of infinitely many closed trajectories is proved.
The ability to track a moving vehicle is of crucial importance in numerous applications. The task has often been approached by the importance sampling technique of particle filters due to its ability to model non-linear and non-Gaussian dynamics, of which a vehicle travelling on a road network is a good example. Partic…
Persistent sampling improves SMC efficiency by retaining and reusing particles.
problem High computational costs and particle impoverishment in SMC.
method Persistent sampling (PS) retains and reuses particles from all prior iterations, using multiple importance sampling and resampling from a mixture of historical distributions.
result PS achieves more accurate posterior approximations and lower variance in marginal likelihood estimates without additional likelihood evaluations.
A computer vision approach improves neutral particle detection in particle flow algorithms.
problem Optimal reconstruction of particle content and kinematics in calorimeter images.
method Computer vision techniques applied to calorimeter images, using deep learning and super-resolution.
result Significantly improved reconstruction of neutral particle calorimeter energy deposits.
Graph Neural Networks model 3D granular flow simulations.
problem Accurate modeling of complex 3D granular flow processes.
method Graph Neural Networks approach to simulate 3D granular flow using LIGGGHTS.
result Machine learning trajectories match physical granular flow processes.
We report a statistical analysis of the Island ECN (NASDAQ) order book. We determine the static and dynamic properties of this system, and then analyze them from a physicist's viewpoint using an equivalent particle system obtained by treating orders as massive particles and price as position. We identify the fundamenta…
Transformers approximate mean-field dynamics of indistinguishable particles.
problem Approximating the dynamics of indistinguishable particles in complex systems.
method Using transformers to model the mean-field dynamics of interacting particle systems.
result Theoretical bounds on the distance between true and transformer-obtained mean-field dynamics.
Paper formulates particle flow using variational inference and Fisher-Rao gradient flow.
problem Estimating posterior densities in probabilistic models.
method Variational formulation of particle flow, Fisher-Rao gradient flow, Gaussian and Gaussian mixture approximations.
result Gaussian and Gaussian mixture approximations of Fisher-Rao particle flow reduce to Exact Daum and Huang particle flow under linear Gaussian assumptions.
In this article, we present the elitist particle filter based on evolutionary strategies (EPFES) as an efficient approach for nonlinear system identification. The EPFES is derived from the frequently-employed state-space model, where the relevant information of the nonlinear system is captured by an unknown state vecto…
New particle algorithms optimize latent variable models.
problem Optimizing latent variable models for maximum likelihood estimation.
method Identify gradient flows associated with free energy functional and discretize them to create particle-based algorithms.
result Novel particle algorithms scale to high-dimensional settings and perform well in experiments.
This paper optimizes functions of probability measures using particle gradient descent for displacement convex functions.
problem Optimizing functions of probability measures with displacement convex properties.
method Particle gradient descent applied to displacement convex functions with theoretical guarantees.
result Finite number of particles and computations are sufficient to find optimal solutions for displacement convex functions.
DPFRL uses particle filters for decision making with complex visual observations.
problem Decision making with partial complex visual observations.
method Discriminative Particle Filter Reinforcement Learning (DPFRL) with a differentiable particle filter in the neural network policy.
result DPFRL outperforms state-of-the-art POMDP RL models in complex visual observation tasks.
A method for optimal Bayesian filtering using progressive particle flow and optimal transport maps.
problem Optimizing Bayesian filtering with deterministic particles to avoid degeneration.
method Progressive flow of particles through a sequence of sub-steps, each using an optimal transport map to replace non-equally weighted particles with equally weighted ones.
result The method avoids particle degeneration and simplifies the filtering process by not requiring inversions or monotonicity constraints.
Optimal weights improve particle-based approximations of discrete distributions.
problem Improving particle-based approximations of discrete distributions.
method Proving optimality of weights and showing how to compute them efficiently.
result Optimal weights can be computed from existing particle-based methods without extra costs.
New approach reduces particle simulation complexity to linear time and space.
problem Challenges in learning dynamics from particle interactions, especially N-body problems.
method Transforms fully-connected interaction graphs into hierarchical ones, reducing complexity.
result Linear time and space complexity for large-scale simulations, retaining high accuracy.
Particle MCMC is a class of algorithms that can be used to analyse state-space models. They use MCMC moves to update the parameters of the models, and particle filters to propose values for the path of the state-space model. Currently the default is to use random walk Metropolis to update the parameter values. We show …
DriftLite improves inference quality of diffusion models without retraining.
problem Adapting pre-trained diffusion models to new target distributions without retraining.
method Lightweight, training-free particle-based approach that steers inference dynamics with optimal stability control.
result Consistently reduces variance and improves sample quality over existing methods.
Paper proposes an end-to-end learning method for state estimation in robotics.
problem Lack of annotated data for optimising dynamic and measurement models in particle filters.
method End-to-end learning objective based on maximising a pseudo-likelihood function.
result Improves state estimation when large portions of true states are unknown.