Del miércoles 23 de abril al viernes 25 de abril se realizarán las X jornadas de orientación profesional con la intervención de miembros del CEP (Centro de Empleo y Prácticas) y conferencias de egresados en Estadística.
Seminario de la profesora Enrica Pirozzi (Dipartimento di afferenza: Dipartimento di Matematica e Fisica (DMF). Università della Campania Luigi Vanvitelli) (https://www.matematicaefisica.unicampania.it/dipartimento/docenti-csa?MATRICOLA=904686) en la sala de conferencias del IMAG. Dos sesiones, el 24 de marzo de 2025, de 9:30-11:00 y de 11:30 a 13:00.
Part I. Fractional stochastic processes for modeling some biological dynamics: theoretical setting, modeling approaches, numerical comparisons and simulations
Part II. Time-changed stochastic models and fractionally integrated processes to model the actin-myosin interaction and dwell times
Seminario de la profesora Giuseppina Albano (Studi Politici e Sociali/DISPS. University of Salerno) (https://docenti.unisa.it/021908/en/curriculum) en la sala de conferencias del IMAG. Dos sesiones, el 26 de marzo de 2025, de 9:30-11:00 y de 11:30 a 13:00.
Part I. Fractional stochastic processes for modeling some biological dynamics: theoretical setting, modeling approaches, numerical comparisons and simulations
Part II. Time-changed stochastic models and fractionally integrated processes to model the actin-myosin interaction and dwell times
Seminario del profesor Tadashi Dohi (School of Informatics and Data Science, Hiroshima University) en la sala de conferencias del IMAG. Dos sesiones, el 27 de marzo de 2025, de 9:30-11:00 y de 11:30 a 13:00.
Las dos sesiones se desarrollarán sobre "Stochastic processes in software reliability"
Seminario del profesor Nikolai Leonenko (Cardiff School of Mathematics. Cardiff University) (https://mathsdemo.cf.ac.uk/maths/contactsandpeople/profiles/leonenkoN.html) en la sala de conferencias del IMAG. Dos sesiones, el 28 de marzo de 2025, de 9:30-11:00 y de 11:30 a 13:00.
Fractional hyperbolic diffusions on sphere with random data
Part I. Introduction to statistical analysis of Gaussian isotropic spherical random fields
Part II. Fractional hyperbolic diffusions on sphere with random data
Seminario del profesor Mogens Bladt en la sala de conferencias del IMAG. Dos sesiones, el 19 de marzo de 2025, de 9:30-11:00 y de 11:30 a 13:00.
1. Introduction to inhomogeneous Markov jump processes and product integration.
2. Inhomogeneous phase-type distributions, IPH.
3. The distribution of rewards.
4. Application to life insurance (survival analysis).
5. Heavy-tailed IPH distributions and insurance risk.
6. Estimation of IPH using the EM algorithm.
7. Stochastic interest rates and IPH.
8. Fitting stochastic interest rates from observed bond prices (IPH fitting)
9. Outlook towards stochastic mortality rates.
Seminario del profesor Krzysztof Podgórski en la sala de conferencias del IMAG. Dos sesiones, el 20 de marzo de 2025, de 9:30-11:00 y de 11:30 a 13:00.
El prof. Jorge Mateu, Departamento de Matemáticas, Universitat Jaume I, Castellón (mateu@uji.es, https://www3.uji.es/~mateu ) impartirá el miércoles 5 de marzo de 2025, a las 12:00 en el Salón de Grados, Facultad de Ciencias la conferencia "Statistical learning for spatio-temporal point processes".
Resumen:
This seminar is focussed on using neural network strategies when dealing with spatio-temporal point processes.
First problem. Given two spatial point patterns, random similarities or differences between them provide no information about the underlying differences between their corresponding generative point processes, and only structural similarities or differences are of interest. To this end, major determinants of given point patterns that include the most relevant information about the underlying point processes that have generated the observed point patterns must be extracted by a suitable transformation. Such transformation is called feature extraction in machine learning and pattern recognition literature. Here we use neural network methods to distinguish between generative processes and provide a classification method for new arrivals.
Second problem. We propose a framework of spatio-temporal-network point processes for modeling crime events observed within street networks in urban areas. The framework incorporates the city street network structure as the underlying space of the crime events' occurrences, and uses a street network-based distance to measure the distance between events living in the continuous geographic space. We extend the definition of the event mark by concatenating the crime category of the event and the type of its nearby city landmark. Temporal and street distance-based spatial kernel functions are adopted to characterize the event dependencies over time and the geographic space, and the interactions between crime events with different marks are modeled through a mark interaction network. The learning of the mark interaction network is achieved by incorporating graph neural networks (GNNs) in our influence kernel.
Third problem. While random permutations of point processes are useful for generating counterfactuals in bivariate interaction tests, such permutations require that the underlying intensity be separable. In many real-world datasets where clustering or inhibition is present, such an assumption does not hold. Here, we introduce a simple combinatorial optimization algorithm that generates second-order preserving (SOP) point process permutations, for example, permutations of the times of events such that the L-function of the permuted process matches the L-function of the data. We apply the algorithm to synthetic data generated by a self-exciting Hawkes process and a self-avoiding point process, along with data from Los Angeles on earthquakes and arsons and data from Indianapolis on law enforcement drug seizures and overdoses. In all cases, we are able to generate a diverse sample of permuted point processes where the distribution of the L-functions closely matches that of the data.
Fourth problem. Previous research demonstrated that second order statistics such as the K-function could not reliably be used to distinguish between log Gaussian Cox (LGCP) and Hawkes processes. However, recent work suggests that machine learning algorithms such as convolutional neural networks (CNN) may be able to differentiate spatial point patterns. The use of a CNN allows for higher level features to be used to distinguish between point patterns that perhaps are indistinguishable by the human eye or through conventional statistics, especially first or second order statistics. Here, we analyze whether convolutional neural networks can aid in distinguishing Hawkes processes from LGCPs and offer recommendations for model selection between these two types of spatio-temporal clustering processes.
Organiza: Academia de Ciencias Matemáticas, Físico-Químicas y Naturales de Granada, con la colaboración del Máster Universitario en Estadística Aplicada (UGR)
Dentro del ciclo de eminarios organizados por los nodos UGr-IO Y UGr-Prob de la la RED2022-134435-T (RED DE PROCESOS ESTOCÁSTICOS Y SUS APLICACIONES) comenzará el próximo 06/03/2025 a las 9:00-9:30 hasta las 13:00.
La primera charla será impartida por el Profesor Antonio Di Crescenzo (Department of Mathematics. University of Salerno (https://docenti.unisa.it/005305/en/curriculum), titulada:
Finite-velocity random motions and reset at the origin: Recent advances on transient and limit behaviors
SEDE: IMAG. Sala de Conferencias
Más información en: https://sites.google.com/view/redpresa/actividades-de-la-red/actividades-del-semestre-4.
Seminario 1: Growths equations and their stochastic generalizations: modeling and
inference.
14 de enero de 2025. Seminario 1 del IMAG. 9:00 horas
In this seminar the introduction of stochasticity in growth equations is developed. In
particular, the introduction of noise within the growth equations is discussed, distinguishing
between multiplicative and additive noises. The resulting stochastic diffusion processes
and their parametric inference procedures are discussed. Results for a general growth
curve including a wide family of growth phenomena are shown. Maximum likelihood
method is discussed, and its solution is obtained by means of metaheuristic techniques.
Several simulation studies and an application to real data are performed. The discussion of
the topics will be approached from an informal and not analytic point of view, to provide
students with the basic idea of these topics, favoring the intuitive aspect over
methodological rigor.
Seminario 2: Stochastic SIR model including growths: modeling and inference.
15 de enero de 2025. Seminario 1 del IMAG. 9:00 horas
In this talk the focus is on epidemiological models. In particular, the background of
Susceptible-Infected- Removed model is discussed, emphasizing the role of the
contribution of each subpopulation. The role of stochasticity in such models is also
addressed. However, the main contribution is made to the inference for SIR models. For a
SIR stochastic model, able to include the natural growth of the Susceptible population, the
inference is addressed by means of a quasi-maximum likelihood method. Numerical
procedures for determining the local maxima of the likelihood function are discussed.
Emphasis is placed on the problems associated with the use of such techniques and some
insights are provided.
