B\'ezier Curve Gaussian Processes
- URL: http://arxiv.org/abs/2205.01754v1
- Date: Tue, 3 May 2022 19:49:57 GMT
- Title: B\'ezier Curve Gaussian Processes
- Authors: Ronny Hug, Stefan Becker, Wolfgang H\"ubner, Michael Arens, J\"urgen
Beyerer
- Abstract summary: This paper proposes a new probabilistic sequence model building on probabilistic B'ezier curves.
Combined with a Mixture Density network, Bayesian conditional inference can be performed without the need for mean field variational approximation.
The model is used for pedestrian trajectory prediction, where a generated prediction also serves as a GP prior.
- Score: 8.11969931278838
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Probabilistic models for sequential data are the basis for a variety of
applications concerned with processing timely ordered information. The
predominant approach in this domain is given by neural networks, which
incorporate either stochastic units or components. This paper proposes a new
probabilistic sequence model building on probabilistic B\'ezier curves. Using
Gaussian distributed control points, these parametric curves pose a special
case for Gaussian processes (GP). Combined with a Mixture Density network,
Bayesian conditional inference can be performed without the need for mean field
variational approximation or Monte Carlo simulation, which is a requirement of
common approaches. For assessing this hybrid model's viability, it is applied
to an exemplary sequence prediction task. In this case the model is used for
pedestrian trajectory prediction, where a generated prediction also serves as a
GP prior. Following this, the initial prediction can be refined using the GP
framework by calculating different posterior distributions, in order to adapt
more towards a given observed trajectory segment.
Related papers
- von Mises Quasi-Processes for Bayesian Circular Regression [57.88921637944379]
We explore a family of expressive and interpretable distributions over circle-valued random functions.
The resulting probability model has connections with continuous spin models in statistical physics.
For posterior inference, we introduce a new Stratonovich-like augmentation that lends itself to fast Markov Chain Monte Carlo sampling.
arXiv Detail & Related papers (2024-06-19T01:57:21Z) - Fusion of Gaussian Processes Predictions with Monte Carlo Sampling [61.31380086717422]
In science and engineering, we often work with models designed for accurate prediction of variables of interest.
Recognizing that these models are approximations of reality, it becomes desirable to apply multiple models to the same data and integrate their outcomes.
arXiv Detail & Related papers (2024-03-03T04:21:21Z) - A Bayesian Take on Gaussian Process Networks [1.7188280334580197]
This work implements Monte Carlo and Markov Chain Monte Carlo methods to sample from the posterior distribution of network structures.
We show that our method outperforms state-of-the-art algorithms in recovering the graphical structure of the network.
arXiv Detail & Related papers (2023-06-20T08:38:31Z) - Joint Bayesian Inference of Graphical Structure and Parameters with a
Single Generative Flow Network [59.79008107609297]
We propose in this paper to approximate the joint posterior over the structure of a Bayesian Network.
We use a single GFlowNet whose sampling policy follows a two-phase process.
Since the parameters are included in the posterior distribution, this leaves more flexibility for the local probability models.
arXiv Detail & Related papers (2023-05-30T19:16:44Z) - Gaussian Graphical Models as an Ensemble Method for Distributed Gaussian
Processes [8.4159776055506]
We propose a novel approach for aggregating the Gaussian experts' predictions by Gaussian graphical model (GGM)
We first estimate the joint distribution of latent and observed variables using the Expectation-Maximization (EM) algorithm.
Our new method outperforms other state-of-the-art DGP approaches.
arXiv Detail & Related papers (2022-02-07T15:22:56Z) - Non-Gaussian Gaussian Processes for Few-Shot Regression [71.33730039795921]
We propose an invertible ODE-based mapping that operates on each component of the random variable vectors and shares the parameters across all of them.
NGGPs outperform the competing state-of-the-art approaches on a diversified set of benchmarks and applications.
arXiv Detail & Related papers (2021-10-26T10:45:25Z) - Gaussian Processes to speed up MCMC with automatic
exploratory-exploitation effect [1.0742675209112622]
We present a two-stage Metropolis-Hastings algorithm for sampling probabilistic models.
The key feature of the approach is the ability to learn the target distribution from scratch while sampling.
arXiv Detail & Related papers (2021-09-28T17:43:25Z) - Pathwise Conditioning of Gaussian Processes [72.61885354624604]
Conventional approaches for simulating Gaussian process posteriors view samples as draws from marginal distributions of process values at finite sets of input locations.
This distribution-centric characterization leads to generative strategies that scale cubically in the size of the desired random vector.
We show how this pathwise interpretation of conditioning gives rise to a general family of approximations that lend themselves to efficiently sampling Gaussian process posteriors.
arXiv Detail & Related papers (2020-11-08T17:09:37Z) - Improving predictions of Bayesian neural nets via local linearization [79.21517734364093]
We argue that the Gauss-Newton approximation should be understood as a local linearization of the underlying Bayesian neural network (BNN)
Because we use this linearized model for posterior inference, we should also predict using this modified model instead of the original one.
We refer to this modified predictive as "GLM predictive" and show that it effectively resolves common underfitting problems of the Laplace approximation.
arXiv Detail & Related papers (2020-08-19T12:35:55Z)
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.