Towards Differentiable Resampling

• URL: http://arxiv.org/abs/2004.11938v1
• Date: Fri, 24 Apr 2020 18:37:17 GMT
• Title: Towards Differentiable Resampling
• Authors: Michael Zhu, Kevin Murphy, Rico Jonschkowski
• Abstract summary: We present a novel network architecture, the particle transformer, and train it for particle resampling using a likelihood-based loss function over sets of particles. Our results show that our learned resampler outperforms traditional resampling techniques on synthetic data and in a simulated robot localization task.
• Score: 22.92540370475242
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Resampling is a key component of sample-based recursive state estimation in particle filters. Recent work explores differentiable particle filters for end-to-end learning. However, resampling remains a challenge in these works, as it is inherently non-differentiable. We address this challenge by replacing traditional resampling with a learned neural network resampler. We present a novel network architecture, the particle transformer, and train it for particle resampling using a likelihood-based loss function over sets of particles. Incorporated into a differentiable particle filter, our model can be end-to-end optimized jointly with the other particle filter components via gradient descent. Our results show that our learned resampler outperforms traditional resampling techniques on synthetic data and in a simulated robot localization task.

Related papers

• Permutation Invariant Learning with High-Dimensional Particle Filters [8.878254892409005]
  Sequential learning in deep models often suffers from challenges such as catastrophic forgetting and loss of plasticity. We introduce a novel permutation-invariant learning framework based on high-dimensional particle filters.
  arXiv  Detail & Related papers  (2024-10-30T05:06:55Z)
• Regime Learning for Differentiable Particle Filters [19.35021771863565]
  Differentiable particle filters are an emerging class of models that combine sequential Monte Carlo techniques with the flexibility of neural networks to perform state space inference. No prior approaches effectively learn both the individual regimes and the switching process simultaneously. We propose the neural network based regime learning differentiable particle filter (RLPF) to address this problem.
  arXiv  Detail & Related papers  (2024-05-08T07:43:43Z)
• Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler [103.97487121678276]
  Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs. We propose a novel Knowledge-driven Differential Filter Sampler(KDFS) with Masked Filter Modeling(MFM) framework for filter pruning.
  arXiv  Detail & Related papers  (2023-07-01T02:28:41Z)
• An overview of differentiable particle filters for data-adaptive sequential Bayesian inference [19.09640071505051]
  Particle filters (PFs) provide an efficient mechanism for solving non-linear sequential state estimation problems. An emerging trend involves constructing components of particle filters using neural networks and optimising them by gradient descent. Differentiable particle filters are a promising computational tool for performing inference on sequential data in complex, high-dimensional tasks.
  arXiv  Detail & Related papers  (2023-02-19T18:03:53Z)
• Continuous-time Particle Filtering for Latent Stochastic Differential Equations [37.51802583388233]
  We propose continuous latent particle filters, an approach that extends particle filtering to the continuous-time domain. We demonstrate how continuous latent particle filters can be used as a generic plug-in replacement for inference techniques relying on a learned variational posterior.
  arXiv  Detail & Related papers  (2022-09-01T01:05:31Z)
• 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)
• Deep Learning for the Benes Filter [91.3755431537592]
  We present a new numerical method based on the mesh-free neural network representation of the density of the solution of the Benes model. We discuss the role of nonlinearity in the filtering model equations for the choice of the domain of the neural network.
  arXiv  Detail & Related papers  (2022-03-09T14:08:38Z)
• Batch Normalization Tells You Which Filter is Important [49.903610684578716]
  We propose a simple yet effective filter pruning method by evaluating the importance of each filter based on the BN parameters of pre-trained CNNs. The experimental results on CIFAR-10 and ImageNet demonstrate that the proposed method can achieve outstanding performance.
  arXiv  Detail & Related papers  (2021-12-02T12:04:59Z)
• Unrolling Particles: Unsupervised Learning of Sampling Distributions [102.72972137287728]
  Particle filtering is used to compute good nonlinear estimates of complex systems. We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.
  arXiv  Detail & Related papers  (2021-10-06T16:58:34Z)
• Learning Versatile Convolution Filters for Efficient Visual Recognition [125.34595948003745]
  This paper introduces versatile filters to construct efficient convolutional neural networks. We conduct theoretical analysis on network complexity and an efficient convolution scheme is introduced. Experimental results on benchmark datasets and neural networks demonstrate that our versatile filters are able to achieve comparable accuracy as that of original filters.
  arXiv  Detail & Related papers  (2021-09-20T06:07:14Z)
• Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking [1.1531505895603305]
  This work proposes a novel framework for visual tracking based on the integration of an iterative particle filter, a deep convolutional neural network, and a correlation filter. We employ a novel strategy to assess the likelihood of the particles after the iterations by applying K-means clustering. Experimental results on two different benchmark datasets show that our tracker performs favorably against state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-07-07T02:44:43Z)

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.