Time-Varying Transition Matrices with Multi-task Gaussian Processes

• URL: http://arxiv.org/abs/2306.11772v1
• Date: Tue, 20 Jun 2023 15:22:50 GMT
• Title: Time-Varying Transition Matrices with Multi-task Gaussian Processes
• Authors: Ekin Ugurel
• Abstract summary: We present a kernel-based, multi-task Gaussian Process (GP) model for approximating the underlying function of an individual's mobility state. We enforce the constraints of incorporation probabilities in a Markov process through a set of constraint points in the GP. Our numerical experiments demonstrate the ability of our formulation to enforce the desired constraints while learning the functional form of transition probabilities.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we present a kernel-based, multi-task Gaussian Process (GP) model for approximating the underlying function of an individual's mobility state using a time-inhomogeneous Markov Process with two states: moves and pauses. Our approach accounts for the correlations between the transition probabilities by creating a covariance matrix over the tasks. We also introduce time-variability by assuming that an individual's transition probabilities vary over time in response to exogenous variables. We enforce the stochasticity and non-negativity constraints of probabilities in a Markov process through the incorporation of a set of constraint points in the GP. We also discuss opportunities to speed up GP estimation and inference in this context by exploiting Toeplitz and Kronecker product structures. Our numerical experiments demonstrate the ability of our formulation to enforce the desired constraints while learning the functional form of transition probabilities.

Related papers

• A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics [51.147876395589925]
  A non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time. A fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance.
  arXiv  Detail & Related papers  (2024-02-26T04:39:01Z)
• Logistic-beta processes for dependent random probabilities with beta marginals [58.91121576998588]
  We propose a novel process called the logistic-beta process, whose logistic transformation yields a process with common beta marginals. It can model dependence on both discrete and continuous domains, such as space or time, and has a flexible dependence structure through correlation kernels. We illustrate the benefits through nonparametric binary regression and conditional density estimation examples, both in simulation studies and in a pregnancy outcome application.
  arXiv  Detail & Related papers  (2024-02-10T21:41:32Z)
• Entropic Matching for Expectation Propagation of Markov Jump Processes [38.60042579423602]
  We propose a new tractable inference scheme based on an entropic matching framework. We demonstrate the effectiveness of our method by providing closed-form results for a simple family of approximate distributions. We derive expressions for point estimation of the underlying parameters using an approximate expectation procedure.
  arXiv  Detail & Related papers  (2023-09-27T12:07:21Z)
• Work statistics for Quantum Spin Chains: characterizing quantum phase transitions, benchmarking time evolution, and examining passivity of quantum states [0.023020018305241332]
  We use our numerical method to evaluate the moments/cumulants of work done by sudden quench process on the Ising or Haldane spin chains. Second, we propose to use the fluctuation theorem as a benchmark indicator for the numerical real-time evolving methods. Third, we study the passivity of ground and thermal states of quantum spin chains under some cyclic impulse processes.
  arXiv  Detail & Related papers  (2023-08-25T13:22:57Z)
• Deep Stochastic Processes via Functional Markov Transition Operators [59.55961312230447]
  We introduce a new class of Processes (SPs) constructed by stacking sequences of neural parameterised Markov transition operators in function space. We prove that these Markov transition operators can preserve the exchangeability and consistency of SPs.
  arXiv  Detail & Related papers  (2023-05-24T21:15:23Z)
• Estimating Latent Population Flows from Aggregated Data via Inversing Multi-Marginal Optimal Transport [57.16851632525864]
  We study the problem of estimating latent population flows from aggregated count data. This problem arises when individual trajectories are not available due to privacy issues or measurement fidelity. We propose to estimate the transition flows from aggregated data by learning the cost functions of the MOT framework.
  arXiv  Detail & Related papers  (2022-12-30T03:03:23Z)
• Contrastive learning of strong-mixing continuous-time stochastic processes [53.82893653745542]
  Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data. We show that a properly constructed contrastive learning task can be used to estimate the transition kernel for small-to-mid-range intervals in the diffusion case.
  arXiv  Detail & Related papers  (2021-03-03T23:06:47Z)
• The Connection between Discrete- and Continuous-Time Descriptions of Gaussian Continuous Processes [60.35125735474386]
  We show that discretizations yielding consistent estimators have the property of invariance under coarse-graining' This result explains why combining differencing schemes for derivatives reconstruction and local-in-time inference approaches does not work for time series analysis of second or higher order differential equations.
  arXiv  Detail & Related papers  (2021-01-16T17:11:02Z)
• Computational Phase Transitions: Benchmarking Ising Machines and Quantum Optimisers [0.0]
  Hardest instances appear to be well-concentrated in a narrow region, with a control parameter allowing uniform random distributions. It has been established that one could observe a computational phase transition in a distribution produced from coherent Ising machine(s)
  arXiv  Detail & Related papers  (2020-09-11T18:00:00Z)
• Transition probabilities and transition rates in discrete phase space [0.0]
  We show how the transition rates for any Hamiltonian evolution can be worked out by expanding the Hamiltonian as a linear combination of displacement operators in the discrete phase space.
  arXiv  Detail & Related papers  (2020-07-20T15:22:20Z)
• Fast Variational Learning in State-Space Gaussian Process Models [29.630197272150003]
  We build upon an existing method called conjugate-computation variational inference. We provide an efficient JAX implementation which exploits just-in-time compilation. Our approach leads to fast and stable variational inference in state-space GP models that can be scaled to time series with millions of data points.
  arXiv  Detail & Related papers  (2020-07-09T12:06:34Z)

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.