Saved in:
Bibliographic Details
Main Authors: Nazarovs, Jurijs, Huang, Zhichun, Zhen, Xingjian, Pal, Sourav, Chakraborty, Rudrasis, Singh, Vikas
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.11418
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913269496676352
author Nazarovs, Jurijs
Huang, Zhichun
Zhen, Xingjian
Pal, Sourav
Chakraborty, Rudrasis
Singh, Vikas
author_facet Nazarovs, Jurijs
Huang, Zhichun
Zhen, Xingjian
Pal, Sourav
Chakraborty, Rudrasis
Singh, Vikas
contents A deterministic temporal process can be determined by its trajectory, an element in the product space of (a) initial condition $z_0 \in \mathcal{Z}$ and (b) transition function $f: (\mathcal{Z}, \mathcal{T}) \to \mathcal{Z}$ often influenced by the control of the underlying dynamical system. Existing methods often model the transition function as a differential equation or as a recurrent neural network. Despite their effectiveness in predicting future measurements, few results have successfully established a method for sampling and statistical inference of trajectories using neural networks, partially due to constraints in the parameterization. In this work, we introduce a mechanism to learn the distribution of trajectories by parameterizing the transition function $f$ explicitly as an element in a function space. Our framework allows efficient synthesis of novel trajectories, while also directly providing a convenient tool for inference, i.e., uncertainty estimation, likelihood evaluations and out of distribution detection for abnormal trajectories. These capabilities can have implications for various downstream tasks, e.g., simulation and evaluation for reinforcement learning.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11418
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Variational Sampling of Temporal Trajectories
Nazarovs, Jurijs
Huang, Zhichun
Zhen, Xingjian
Pal, Sourav
Chakraborty, Rudrasis
Singh, Vikas
Machine Learning
Artificial Intelligence
A deterministic temporal process can be determined by its trajectory, an element in the product space of (a) initial condition $z_0 \in \mathcal{Z}$ and (b) transition function $f: (\mathcal{Z}, \mathcal{T}) \to \mathcal{Z}$ often influenced by the control of the underlying dynamical system. Existing methods often model the transition function as a differential equation or as a recurrent neural network. Despite their effectiveness in predicting future measurements, few results have successfully established a method for sampling and statistical inference of trajectories using neural networks, partially due to constraints in the parameterization. In this work, we introduce a mechanism to learn the distribution of trajectories by parameterizing the transition function $f$ explicitly as an element in a function space. Our framework allows efficient synthesis of novel trajectories, while also directly providing a convenient tool for inference, i.e., uncertainty estimation, likelihood evaluations and out of distribution detection for abnormal trajectories. These capabilities can have implications for various downstream tasks, e.g., simulation and evaluation for reinforcement learning.
title Variational Sampling of Temporal Trajectories
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2403.11418