English
Related papers

Related papers: Random telegraph processes with non-local memory

200 papers

We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models. RNPs model the state space with Neural Processes. Given time series observed on fast real-world time scales but…

Machine Learning · Computer Science 2019-11-07 Timon Willi , Jonathan Masci , Jürgen Schmidhuber , Christian Osendorfer

Random flights (also called run-and-tumble walks or transport processes) represent finite velocity random motions changing direction at any Poissonian time. These models in d-dimension, can be studied giving a general formulation of the…

Statistical Mechanics · Physics 2024-10-16 Luca Angelani , Alessandro De Gregorio , Roberto Garra , Francesco Iafrate

In environmental applications of extreme value statistics, the underlying stochastic process is often modeled either as a max-stable process in continuous time/space or as a process in the domain of attraction of such a max-stable process.…

Statistics Theory · Mathematics 2018-02-13 Holger Drees , Laurens de Haan , Feridun Turkman

Sequential models like recurrent neural networks and transformers have become standard for probabilistic multivariate time series forecasting across various domains. Despite their strengths, they struggle with capturing high-dimensional…

Machine Learning · Computer Science 2024-10-07 Yu Chen , Marin Biloš , Sarthak Mittal , Wei Deng , Kashif Rasul , Anderson Schneider

Many real world applications can be formulated as event forecasting on Continuous Time Dynamic Graphs (CTDGs) where the occurrence of a timed event between two entities is represented as an edge along with its occurrence timestamp in the…

Machine Learning · Computer Science 2022-05-24 Xuhong Wang , Sirui Chen , Yixuan He , Minjie Wang , Quan Gan , Yupu Yang , Junchi Yan

Temporal exponential random graph models (TERGM) are powerful statistical models that can be used to infer the temporal pattern of edge formation and elimination in complex networks (e.g., social networks). TERGMs can also be used in a…

Social and Information Networks · Computer Science 2024-09-17 Yifan Huang , Clayton Barham , Eric Page , PK Douglas

Modern graph representation learning works mostly under the assumption of dealing with regularly sampled temporal graph snapshots, which is far from realistic, e.g., social networks and physical systems are characterized by continuous…

Machine Learning · Computer Science 2024-09-11 Alessio Gravina , Daniele Zambon , Davide Bacciu , Cesare Alippi

An algorithm for non-stationary spatial modelling using multiple secondary variables is developed. It combines Geostatistics with Quantile Random Forests to give a new interpolation and stochastic simulation algorithm. This paper introduces…

Methodology · Statistics 2022-01-13 Colin Daly

This paper is centered on the random graph generated by a Doeblin-type coupling of discrete time processes on a countable state space whereby when two paths meet, they merge. This random graph is studied through a novel subgraph, called a…

Probability · Mathematics 2018-11-27 François Baccelli , Mir-Omid Haji-Mirsadeghi , James T. Murphy

In real-world scenario, many phenomena produce a collection of events that occur in continuous time. Point Processes provide a natural mathematical framework for modeling these sequences of events. In this survey, we investigate…

We propose a new generalisation of jump-telegraph process with variable velocities and jumps. Amplitude of the jumps and velocity values are random, and they depend on the time spent by the process in the previous state of the underlying…

Probability · Mathematics 2013-11-22 Nikita Ratanov

We propose a new class of parameterizations for spatio-temporal point processes which leverage Neural ODEs as a computational method and enable flexible, high-fidelity models of discrete events that are localized in continuous time and…

Machine Learning · Computer Science 2021-03-19 Ricky T. Q. Chen , Brandon Amos , Maximilian Nickel

A general method is presented to explicitly compute autocovariance functions for non-Poisson dichotomous noise based on renewal theory. The method is specialized to a random telegraph signal of Mittag-Leffler type. Analytical predictions…

Data Analysis, Statistics and Probability · Physics 2009-08-03 Simone Ferraro , Michele Manzini , Aldo Masoero , Enrico Scalas

We consider two independent Goldstein-Kac telegraph processes $X_1(t)$ and $X_2(t)$ on the real line $\Bbb R$, both developing with finite constant speed $c>0$, that, at the initial time instant $t=0$, simultaneously start from the origin…

Probability · Mathematics 2015-06-24 Alexander D. Kolesnik

We calculate the two-point correlation function <x(t2)x(t1)> for a subdiffusive continuous time random walk in a parabolic potential, generalizing well-known results for the single-time statistics to two times. A closed analytical…

Statistical Mechanics · Physics 2009-11-13 A. Baule , R. Friedrich

Neural marked temporal point processes have been a valuable addition to the existing toolbox of statistical parametric models for continuous-time event data. These models are useful for sequences where each event is associated with a single…

Machine Learning · Computer Science 2024-03-20 Yuxin Chang , Alex Boyd , Padhraic Smyth

We propose Markov two-components processes (M2CP) as a probabilistic model of asynchronous systems based on the trace semantics for concurrency. Considering an asynchronous system distributed over two sites, we introduce concepts and tools…

Systems and Control · Computer Science 2015-07-01 Samy Abbes

There has been an increasing interest in modeling continuous-time dynamics of temporal graph data. Previous methods encode time-evolving relational information into a low-dimensional representation by specifying discrete layers of neural…

Machine Learning · Computer Science 2022-06-01 Jin Guo , Zhen Han , Zhou Su , Jiliang Li , Volker Tresp , Yuyi Wang

This paper is concerned with combined inference for point processes on the real line observed in a broken interval. For such processes, the classic history-based approach cannot be used. Instead, we adapt tools from sequential spatial point…

Methodology · Statistics 2015-06-04 M. N. M. van Lieshout

Visibility algorithms are a family of methods to map time series into networks, with the aim of describing the structure of time series and their underlying dynamical properties in graph-theoretical terms. Here we explore some properties of…

Data Analysis, Statistics and Probability · Physics 2015-10-14 Lucas Lacasa , Ryan Flanagan
‹ Prev 1 3 4 5 6 7 10 Next ›