- Random - Mailing list — Dipartimento di Matematica, UniPI

seminario di Chaitanya Joshi all'IMATI-Milano
by Antonella Bodini 06 Sep '16

06 Sep '16

Gentili colleghi, domani, *mercoledi' 7 settembre, alle ore 15 *presso la sede di Milano dell'IMATI, via Corti 12 - sala A, *Chaitanya Joshi,* dall'Universita' di Waikato (Hamilton, Nuova Zelanda) terra' il seminario: * * *Improving grid based Bayesian inference* /Abstract/: In some cases, computational benefit can be gained by exploring the hyper parameter space using a deterministic set of grid points instead of a Markov chain. We view this as a numerical integration problem and make three unique contributions. First, we explore the space using low discrepancy point sets instead of a grid. This allows for accurate estimation of marginals of any shape at a much lower computational cost than a grid based approach and thus makes it possible to extend the computational benefit to a hyper parameter space with higher dimensionality (10 or more). Second, we propose a new, quick and easy method to estimate the marginal using a least squares polynomial and prove the conditions under which this polynomial will converge to the true marginal. Our results are valid for a wide range of point sets including grids, random points and low discrepancy points. Third, we show that further accuracy and efficiency can be gained by taking into consideration the functional decomposition of the integrand and illustrate how this can be done using anchored f-ANOVA on weighted spaces. Tutti gli interessati sono invitati a partecipare. Cordiali saluti, Antonella -- Dott. Antonella Bodini CNR-Istituto di Matematica Applicata e Tecnologie Informatiche Via Bassini 15, 20133 Milano (Italy) *** SI PRENDA NOTA CHE PER LAVORI DI RISTRUTTURAZIONE ATTUALMENTE L'ACCESSO E' DA VIA CORTI 12. *** tel +39 02 23699524 fax +39 02 23699538 http://www.mi.imati.cnr.it/~anto/

1 0

Seminario Christian Olivera a Pisa
by Marta Leocata 02 Sep '16

02 Sep '16

Cari tutti, mercoledì 7 Settembre alle ore 15:00 presso l'Aula Riunioni del Dipartimento di Matematica di Pisa, Dr. Christian Olivera (Univ. Campinas) terrà un seminario dal titolo: "Densities of solutions of SDEs with Singular Coefficients" Abstract: We consider a process given as the solution of a stochastic differential equation with unbounded and integrable drift and multiplicative noise. We study the the existence of the Lebesgue density of that process and upper gaussian estimation. The main tools are the Malliavin calculus and the Zvonkin’s transformation. The work is in collaboration with Ciprian Tudor. Saluti, Marta Leocata

1 0

Phd Position in Stochastic Processes at Universität Paderborn (fwd)
by Michele Gianfelice 02 Sep '16

02 Sep '16

Salve, ricevo ed inoltro l'annuncio informale relativo alla posizione in oggetto. Deadline per inoltrare la domanda è il 16 c.m.. Per ulteriori informazioni contattare il Prof. Martin Kolb scrivendo all'indirizzo kolb(a)math.uni-paderborn.de . Cordialmente, m.gianfelice ---------- Forwarded message ---------- Date: Wed, 17 Aug 2016 09:47:23 +0200 From: Maria Infusino <infusino.maria(a)gmail.com> To: Michele Gianfelice <gianfelice(a)mat.unical.it> Subject: Phd Position in Stochastic Processes at Universität Paderborn Caro Michele, ....... Il professor Martin Kolb mi ha informato di avere una posizione di 4 anni per un dottorato di ricerca sotto la sua supervisione all' Universität Paderborn (Wissenschaftlicher Mitarbeiter , 75 % , 4 Jahre ). Giacché il campo di ricerca è processi stocastici, ho pensato che probabilmente tu conosci qualcuno che potrebbe avere interesse a fare domanda. La scadenza per fare domanda è il 16 settembre 2016 e l' interessato/a può direttamente contattare Martin via e-mail per ulteriori informazioni al seguente indirizzo : kolb(a)math.uni-paderborn.de Grazie e un abbraccio, Maria

1 0

Seminario Martin Huesmann a Pisa
by Marta Leocata 02 Sep '16

02 Sep '16

Cari tutti, mercoledì 7 Settembre alle ore 14:00 presso l'Aula Riunioni del Dipartimento di Matematica di Pisa, Dr. Martin Huesmann (Univ. Bonn) terrà un seminario dal titolo: "Monotonicity preserving transformations for martingale optimal transport and the Skorokhod embedding problem" Abstract: There are many transformations mapping martingales into martingales,e.g. M_t -> M_t^2- <M>_t$. However, looking at solutions to the martingale optimal transport problem it turns out that there are only very few transformations that map optimal martingale couplings into optimal martingale couplings. After a short introduction to and review of the state of the art of martingale optimal transport we will give a characterization of all these monotonicity preserving transformations. In particular, these transformation reveal certain symmetries between different solutions to the martingale optimal transport problem. Moreover, we will show that the transport approach to Skorokhod embedding is a powerful tool to study martingale optimal transport and, in turn, that the new symmetries for martingale optimal transport disclose symmetries for solutions to the Skorokhod embedding problem. (based on joint work with Florian Stebegg) Saluti, Marta Leocata

1 0

Fwd: Job openings at the Research Center for Statistics (Geneva School of Economics and Management)
by enea giuseppe bongiorno 01 Sep '16

01 Sep '16

Inoltro con preghiera di diffusione. Scusandomi per invii multipli. E.Bongiorno ---------- Forwarded message ---------- From: Eva Cantoni <Eva.Cantoni(a)unige.ch> Date: 2016-08-31 21:38 GMT+02:00 Subject: Job openings at the Research Center for Statistics (Geneva School of Economics and Management) To: Dear colleagues, (sorry for cross posting) we have an open position at the Assistant professor level in statistics. Please see the ad at: https://www.unige.ch/gsem/rcs/jobs/ May I ask you to distribute the information to potential candidates in your network ? Best wishes, Eva -- Prof. Eva Cantoni Research Center for Statistics and Geneva School of Economics and Management University of Geneva, Bd du Pont d'Arve 40, CH-1211 Genève 4 gsem.unige.ch/rcs/cantoni

1 0

Assegno di ricerca presso la Scuola Normale Superiore, Pisa
by Fabrizio Lillo 01 Sep '16

01 Sep '16

The call for a two-year postdoc is open at the Scuola Normale Superiore di Pisa (Italy). The topic of the research is Optimal execution and market impact models in financial markets The details of the call are at Italian *http://www.sns.it/bando/assegno-di-ricerca-denominato-%E2%80%9Cesecuzione-ottimale-e-modelli-di-market-impact-mercati-finanziari%E2%80%9D-la-collaborazione-al-progetto <http://www.sns.it/bando/assegno-di-ricerca-denominato-%E2%80%9Cesecuzione-o…>* English *http://en.sns.it/bando/research-contract-named-%E2%80%9Coptimal-execution-and-market-impact-models-financial-markets%E2%80%9D-part <http://en.sns.it/bando/research-contract-named-%E2%80%9Coptimal-execution-a…>* The deadline is September 26. I would be grateful if you could forward this message to any potentially interested candidate. The interested candidates can either contact me (fabrizio.lillo(a)sns.it) or the addresses in the call in case they need further information. Thanks and all the best, Fabrizio Lillo ---------------------------------------- Fabrizio Lillo Scuola Normale Superiore Piazza dei Cavalieri 7 56126 Pisa ITALY New website: fabriziolillo.wordpress.com phone: +39 050509159

1 0

seminario
by Brunero Liseo 31 Aug '16

31 Aug '16

Avviso di Seminario When September 8th 2016, 14:30 Where Sapienza Università di Roma facoltà di Economia Aula Fanfani, V piano Viale del Castro Laurenziano, 9 Speaker *Federico Camerlenghi* Università Luigi Bocconi, Milano Titolo *Distribution theory for hierarchical processes with statistical applications* Abstract In Bayesian nonparametrics, a large amount of literature has been carried out under the assumption that observations are exchangeable. However in a large variety of applications this may appear too restrictive, a typical example is when data are generated by different experiments: even if these experiments may be related, they have some specific features that induce heterogeneity across observations. In such a situation data are usually divided into different groups, and a more appropriate assumption is partial exchangeability. In particular the construction of dependent random probability measures to deal with partially exchangeable observations has recently attracted great attention in Bayesian nonparametric literature. In this talk we define and investigate general classes of nonparametric priors, namely hierarchical models, based on transformations of completely random measures. We are able to study all the analytical properties, i.e. the random partition structure, the predictive distributions and the posterior characterization of the processes. Finally some relevant applications to species sampling problems and survival analysis will be discussed. (This is a joint work with A. Lijoi, P. Orbanz and I. Prunster.) -- ============================================ Brunero Liseo *Dip. di metodi e modelli per il territorio, l'economia e la finanza * *Sapienza Università di Roma* *Viale Castro Laurenziano, 9 Roma I-00161 *Tel. +39 06 49766973 Fax +39 06 4957606 *http://www.memotef.uniroma1.it/users/liseo-brunero <http://www.memotef.uniroma1.it/users/liseo-brunero>* =============================================

1 0

seminario Steven Scott (Google) 2/9 in Bicocca
by fabio.bellini 30 Aug '16

30 Aug '16

Cari colleghi, vi segnalo che il giorno venerdì 2 settembre alle ore 17, presso la Aula Martini al piano interrato dell'edificio U6, Steven Scott, Director of Statistics Research at Google, terrà un seminario su Predicting the Present with Bayesian Structural Time Series This article describes a system for short term forecasting based on an ensemble prediction that averages over different combinations of predictors. The system combines a structural time series model for the target series with regression component capturing the contributions of contemporaneous search query data. A spike-and-slab prior on the regression coefficients induces sparsity, dramatically reducing the size of the regression problem. Our system averages over potential contributions from a very large set of models and gives easily digested reports of which coefficients are likely to be important. We illustrate with applications to initial claims for unemployment benefits and to retail sales. Although our exposition focuses on using search engine data to forecast economic time series, the underlying statistical methods can be applied to more general short term forecasting with large numbers of contemporaneous predictors (joint work with Hal Varian). L'evento è organizzato in collaborazione con Innovation Pub e sarà seguito da un piccolo rinfresco. Sarà inoltre possibile seguire lo streaming su http://streaming.unimib.it/.

1 0

Third StaTalk on Computational Tools for Statistical Modelling.
by Clara Grazian 29 Aug '16

29 Aug '16

Dear all, we are pleased to announce that the third meeting of the *StaTalk* series will be held at *Facoltà di Economia di Sapienza Università di Roma *on *September 9, 2016*. StaTalks are one-day workshops on statistical topics during which the hosting group introduces and overviews the main research interests of their members. Aimed at Master’s and PhD students, as well as at post-docs and young researchers, StaTalks are intended to be informal gatherings which allow for a more proficient interaction between presenters and participants. They typically feature some introductory tutorials on the main workshop theme and a few seminars that overview more advanced research topics, still kept at an expository level. StaTalks are thus a great opportunity to become acquainted with the workshop main topic, as well as to share and update one's knowledge on the interface of Statistical research in an easy and informal atmosphere. StaTalks are endorsed by Y-SIS ( https://sites.google.com/site/youngsocietaitalianastatistica/) the young section of the Italian Statistical Society. The topic of the third StaTalk will be on *Computational Tools for Statistical Modelling*. We will present and discuss both standard and new computational methods which represents fundamental tools for new challenging applications, such as economic, finance, genetic and official statistics. *Programme* *09.30-10.00 *Opening *10.00-10.40 *Christian Macaro (SAS System) "*A mixture of heterogeneous models with time dependent weights*" *10.40-11.10* Coffee break *11.10-11.50* Clara Grazian (MEMOTEF Department) "*Modelling financial dependence through approximate Bayesian inference*" *11.50-12.30* Stefano Vaccari (MEMOTEF Department) "*Pricing in the Presence of Social Learning: Modelling Information Aggregation in a Competitive Market*" *12.30-14.30* Lunch break *14.30-15.10 *Andrea Tancredi (MEMOTEF Department) "*A Bayesian approach for de-duplication, record linkage and inference with linked data.*" *15.10-15.50 *Luca Tardella (Department of Statistical Science) "*Alternative approaches for approximating marginal likelihood.*" *15.50-16.30* Davide Di Cecco (ISTAT) "*Towards the use of administrative sources in official statistics: Some examples of methodologies for administrative multi source integration utilized at ISTAT.*" *16.30-17.00 *Closing Additional info can be found at the workshop page https://sites.google.com/site/youngsocietaitalianastatistica/events/statalk… or by writing to clara.grazian(a)uniroma1.it. REGISTRATION to the third StaTalk is now open. *No conference fees are due, but registration is mandatory*, using the form available on the website. Clara Grazian PhD in Statistics Research Fellow *Memotef* *Facoltà di Economia* *Sapienza Università di Roma* via del Castro Laurenziano 9, 00161, Roma

1 0

Padova: call for interest for two positions at the level of Associate Professor
by Tiziano Vargiolu 25 Aug '16

25 Aug '16

Call for interest for two positions at the level of Associate Professor ============================================================= The Department of Mathematics of the University of Padova is seeking to fill two positions at the level of Associate Professor through direct appointment (Italian "chiamata diretta") or open competitive selection (Italian "concorso"). The call is open to scientists working in Mathematics or Computer Science. Candidates must be in possession of the Italian Scientific Qualification as Associate Professor ("abilitazione scientifica nazionale di seconda fascia") or hold a position equivalent to that of Italian Associate Professor at a foreign University or Research Institute. Candidates are asked to submit (at direzione(a)math.unipd.it) their CV and a letter of interest by 5th September 2016. Prospective candidates will be invited to the Department of Mathematics for a seminar talk and discussion with members of the Department. The Department plans to decide by the end of October 2016 whether to proceed with direct appointment or open competitive selection. In the case of open competitive selection a choice of the area (Italian "settore concorsuale) will be made and the selection is expected to take place in the first half of 2017. Tiziano -------------------------------------------------------------------------- Tiziano Vargiolu Dipartimento di Matematica Phone: +39 049 8271383 Universita' di Padova Fax: +39 049 8271428 Via Trieste, 63 E-mail: vargiolu(a)math.unipd.it I-35121 Padova (Italy) WWW: http://www.math.unipd.it/~vargiolu -------------------------------------------------------------------------- ---------- Forwarded message ---------- Date: Mon, 25 Jul 2016 09:00:28 +0200 From: Marco Ferrante <ferrante(a)math.unipd.it> To: afferenti(a)math.unipd.it Subject: Call per PA di settembre Cari colleghi, nelle news di dipartimento con link http://www.math.unipd.it/it/news/?id=1894 abbiamo inserito la call in inglese presentata all'ultimo CdD per le due posizioni da PA che valuteremo a settembre. Vi invito a segnalarla ai colleghi che voleste contattare Marco -- Prof. Marco Ferrante Dipartimento di Matematica Universit? degli Studi di Padova Via Trieste 63 , I-35121 Padova - ITALY Tel: +39-0498271366 Fax: +39-0498271499 E-Mail: ferrante(a)math.unipd.it URL: http://www.math.unipd.it/~ferrante

1 0