Convergence analysis of kernel learning FBSDE filter

• URL: http://arxiv.org/abs/2405.13390v3
• Date: Fri, 28 Jun 2024 21:45:11 GMT
• Title: Convergence analysis of kernel learning FBSDE filter
• Authors: Yunzheng Lyu, Feng Bao,
• Abstract summary: Kernel learning forward backward SDE filter is an iterative and adaptive meshfree approach to solve the nonlinear filtering problem. It builds from forward backward SDE for Fokker-Planker equation, which defines evolving density for the state variable, and employs to approximate density.
• Score: 0.8528368686417979
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Kernel learning forward backward SDE filter is an iterative and adaptive meshfree approach to solve the nonlinear filtering problem. It builds from forward backward SDE for Fokker-Planker equation, which defines evolving density for the state variable, and employs KDE to approximate density. This algorithm has shown more superior performance than mainstream particle filter method, in both convergence speed and efficiency of solving high dimension problems. However, this method has only been shown to converge empirically. In this paper, we present a rigorous analysis to demonstrate its local and global convergence, and provide theoretical support for its empirical results.

Related papers

• High-dimensional Bayesian filtering through deep density approximation [0.0]
  We benchmark two recently developed deep density methods for nonlinear filtering.<n>The two filters: the deep splitting filter and the deep BSDE filter, are both based on Feynman--Kac formulas, Euler--Maruyama discretizations and neural networks.<n>In terms of computational efficiency, the deep density methods reduce inference time by roughly two to five orders of magnitude relative to the particle-based filters.
  arXiv  Detail & Related papers  (2025-11-10T16:06:31Z)
• A PDE-Based Image Dehazing Method via Atmospheric Scattering Theory [21.305574997938685]
  We introduce a novel partial differential equation (PDE) framework for single-image dehazing.<n>A key innovation is an adaptive regularization mechanism guided by the dark channel prior.<n>Experiments confirm our method effective haze removal while preserving high image fidelity.
  arXiv  Detail & Related papers  (2025-06-10T13:43:09Z)
• Adversarial Transform Particle Filters [11.330617592263744]
  The particle filter (PF) and the ensemble Kalman filter (EnKF) are widely used for approximate inference in state-space models. We propose the Adversarial Transform Particle Filter (ATPF), a novel filtering framework that combines the strengths of the PF and the EnKF through adversarial learning.
  arXiv  Detail & Related papers  (2025-02-10T05:31:35Z)
• Closed-form Filtering for Non-linear Systems [83.91296397912218]
  We propose a new class of filters based on Gaussian PSD Models, which offer several advantages in terms of density approximation and computational efficiency. We show that filtering can be efficiently performed in closed form when transitions and observations are Gaussian PSD Models. Our proposed estimator enjoys strong theoretical guarantees, with estimation error that depends on the quality of the approximation and is adaptive to the regularity of the transition probabilities.
  arXiv  Detail & Related papers  (2024-02-15T08:51:49Z)
• Gaussian Mixture Solvers for Diffusion Models [84.83349474361204]
  We introduce a novel class of SDE-based solvers called GMS for diffusion models. Our solver outperforms numerous SDE-based solvers in terms of sample quality in image generation and stroke-based synthesis.
  arXiv  Detail & Related papers  (2023-11-02T02:05:38Z)
• Nonlinear Filtering with Brenier Optimal Transport Maps [4.745059103971596]
  This paper is concerned with the problem of nonlinear filtering, i.e., computing the conditional distribution of the state of a dynamical system. Conventional sequential importance resampling (SIR) particle filters suffer from fundamental limitations, in scenarios involving degenerate likelihoods or high-dimensional states. In this paper, we explore an alternative method, which is based on estimating the Brenier optimal transport (OT) map from the current prior distribution of the state to the posterior distribution at the next time step.
  arXiv  Detail & Related papers  (2023-10-21T01:34:30Z)
• An Optimization-based Deep Equilibrium Model for Hyperspectral Image Deconvolution with Convergence Guarantees [71.57324258813675]
  We propose a novel methodology for addressing the hyperspectral image deconvolution problem. A new optimization problem is formulated, leveraging a learnable regularizer in the form of a neural network. The derived iterative solver is then expressed as a fixed-point calculation problem within the Deep Equilibrium framework.
  arXiv  Detail & Related papers  (2023-06-10T08:25:16Z)
• Sampling with Mollified Interaction Energy Descent [57.00583139477843]
  We present a new optimization-based method for sampling called mollified interaction energy descent (MIED) MIED minimizes a new class of energies on probability measures called mollified interaction energies (MIEs) We show experimentally that for unconstrained sampling problems our algorithm performs on par with existing particle-based algorithms like SVGD.
  arXiv  Detail & Related papers  (2022-10-24T16:54:18Z)
• Computational Doob's h-transforms for Online Filtering of Discretely Observed Diffusions [65.74069050283998]
  We propose a computational framework to approximate Doob's $h$-transforms. The proposed approach can be orders of magnitude more efficient than state-of-the-art particle filters.
  arXiv  Detail & Related papers  (2022-06-07T15:03:05Z)
• Variational Kalman Filtering with Hinf-Based Correction for Robust Bayesian Learning in High Dimensions [2.294014185517203]
  We address the problem of convergence of sequential variational inference filter (VIF) through the application of a robust variational objective and Hinf-norm based correction. A novel VIF- Hinf recursion that employs consecutive variational inference and Hinf based optimization steps is proposed.
  arXiv  Detail & Related papers  (2022-04-27T17:38:13Z)
• Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo [60.785586069299356]
  This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance. Our theoretical analysis is further validated by numerical experiments.
  arXiv  Detail & Related papers  (2021-09-08T18:00:05Z)
• Large-Scale Wasserstein Gradient Flows [84.73670288608025]
  We introduce a scalable scheme to approximate Wasserstein gradient flows. Our approach relies on input neural networks (ICNNs) to discretize the JKO steps. As a result, we can sample from the measure at each step of the gradient diffusion and compute its density.
  arXiv  Detail & Related papers  (2021-06-01T19:21:48Z)
• Stochastic Gradient Variance Reduction by Solving a Filtering Problem [0.951828574518325]
  Deep neural networks (DNN) are typically using optimized gradient descent (SGD) The estimation of the gradient using samples tends to be noisy and unreliable, resulting in large gradient variance and bad convergence. We propose textbfFilter Gradient Decent(FGD), an efficient optimization algorithm that makes the consistent estimation of gradient.
  arXiv  Detail & Related papers  (2020-12-22T23:48:42Z)
• On Distributed Non-convex Optimization: Projected Subgradient Method For Weakly Convex Problems in Networks [13.385373310554327]
  The Moreau subgradient method converges linear sharpness problems in machine learning. A distributed implementation of the subgradient method with a theoretical guarantee is proposed.
  arXiv  Detail & Related papers  (2020-04-28T01:01:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.