Robust volatility updates for Hierarchical Gaussian Filtering

• URL: http://arxiv.org/abs/2605.00966v1
• Date: Fri, 01 May 2026 15:33:09 GMT
• Title: Robust volatility updates for Hierarchical Gaussian Filtering
• Abstract summary: HGF networks allow for efficient updating of posterior distributions (beliefs) about hidden states of an agent's environment.<n>New information entering at input nodes leads to a cascade of belief updates across the network.<n>The original form of the update equations for variance-targeting parents(volatility coupling) can in some regions of parameter space lead to negative posterior precision.<n>We introduce a modified quadratic approximation to the variational energy of volatility-coupled nodes that avoids negative posterior precision.
• Score: 0.13194391758295113
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hierarchical Gaussian Filtering (HGF) networks allow for efficient updating of posterior distributions (beliefs) about hidden states of an agent's environment. HGF parent nodes can target the mean or variance of their children. New information entering at input nodes leads to a cascade of belief updates across the network according to one-step update equations for each node's mean and precision (inverse variance). However, the original form of the update equations for variance-targeting parents(volatility coupling) can in some regions of parameter space lead to negative posterior precision, a logical impossibility which causes the updating algorithm to terminate with an error. In this report, we introduce a modified quadratic approximation to the variational energy of volatility-coupled nodes that avoids negative posterior precision. The key idea is to interpolate between two quadratic expansions of the variational energy: one at the prior prediction and one at a second mode whose location is obtained in closed form via the Lambert W function. The resulting update equations are robust across the entire parameter space and faithfully track the variational posterior even for large prediction errors.

Related papers

• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• Decoupled-Value Attention for Prior-Data Fitted Networks: GP Inference for Physical Equations [0.3823356975862005]
  Prior-data fitted networks (PFNs) are a promising alternative to time-consuming Gaussian Process (GP) inference for creating fast surrogates of physical systems.<n>We introduce Decoupled-Value Attention (DVA), motivated by the GP property that the function space is fully characterized by the kernel over inputs.<n>We demonstrate that the crucial factor for scaling PFNs is the attention rule rather than the architecture itself.
  arXiv  Detail & Related papers  (2025-09-25T09:32:42Z)
• Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points [54.06226763868876]
  Wasserstein flow (WGF) is a common method to perform optimization over the space of measures.<n>We show that PWGF converges to a global optimum in terms of general non objectives.
  arXiv  Detail & Related papers  (2025-09-21T08:14:20Z)
• Efficient Link Prediction via GNN Layers Induced by Negative Sampling [86.87385758192566]
  Graph neural networks (GNNs) for link prediction can loosely be divided into two broad categories.<n>We propose a novel GNN architecture whereby the emphforward pass explicitly depends on emphboth positive (as is typical) and negative (unique to our approach) edges.<n>This is achieved by recasting the embeddings themselves as minimizers of a forward-pass-specific energy function that favors separation of positive and negative samples.
  arXiv  Detail & Related papers  (2023-10-14T07:02:54Z)
• Projective Integral Updates for High-Dimensional Variational Inference [0.0]
  Variational inference seeks to improve uncertainty in predictions by optimizing a simplified distribution over parameters to stand in for the full posterior. This work introduces a fixed-point optimization for variational inference that is applicable when every feasible log density can be expressed as a linear combination of functions from a given basis. A PyTorch implementation of QNVB allows for better control over model uncertainty during training than competing methods.
  arXiv  Detail & Related papers  (2023-01-20T00:38:15Z)
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks [64.92221119723048]
  Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. We propose Graph-adaptive Rectified Linear Unit (GReLU) which is a new parametric activation function incorporating the neighborhood information in a novel and efficient way. We conduct comprehensive experiments to show that our plug-and-play GReLU method is efficient and effective given different GNN backbones and various downstream tasks.
  arXiv  Detail & Related papers  (2022-02-13T10:54:59Z)
• Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach [38.45568741734893]
  Inference in our GP model is done by a single feed forward pass through the network, significantly faster than semi-amortized methods. We show that our approach attains higher test data likelihood than the state-of-the-arts on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-02-05T13:01:12Z)
• Uncertainty Inspired RGB-D Saliency Detection [70.50583438784571]
  We propose the first framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Inspired by the saliency data labeling process, we propose a generative architecture to achieve probabilistic RGB-D saliency detection. Results on six challenging RGB-D benchmark datasets show our approach's superior performance in learning the distribution of saliency maps.
  arXiv  Detail & Related papers  (2020-09-07T13:01:45Z)
• Temporal Action Localization with Variance-Aware Networks [12.364819165688628]
  This work addresses the problem of temporal action localization with Variance-Aware Networks (VAN) VANp is a network that propagates the mean and the variance throughout the network to deliver outputs with second order statistics. Results show that VANp surpasses the accuracy of virtually all other two-stage networks without involving any additional parameters.
  arXiv  Detail & Related papers  (2020-08-25T20:12:59Z)
• Variational Hyper-Encoding Networks [62.74164588885455]
  We propose a framework called HyperVAE for encoding distributions of neural network parameters theta. We predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(theta)
  arXiv  Detail & Related papers  (2020-05-18T06:46:09Z)

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.