- Random - Mailing list — Dipartimento di Matematica, UniPI

Colloquium Fabio Lucio Toninelli a Roma Tre
by pietro caputo 21 Feb '14

21 Feb '14

Mercoledi' 26 febbraio 2014 Ore 16:00, Aula F Dip. Matematica e Fisica Roma Tre EDIFICIO AULE LARGO SAN L. MURIALDO,1 Colloquium di Matematica Fabio Toninelli (Universita' di Lione) Random tilings, Glauber dynamics and macroscopic shapes I "piastrellamenti" (tiling) del piano sono un oggetto classico in meccanica statistica e combinatoria. Se le "piastrelle" sono a forma di losanga, si ha una corrispondenza esatta con le interfacce del modello di Ising 3-dimensionale a temperatura nulla. A ogni piastrellamento e' possibile associare una funzione di altezza (superficie discreta). E' ben noto [Cohn-Kenyon-Propp] che, se la taglia della regione U da piastrellare tende all'infinito, la funzione altezza associata a un piastrellamento scelto uniformemente tende verso una certa forma limite macroscopica che risolve una PDE ellittica non-lineare. Sull'insieme dei piastrellamenti si puo' definire una dinamica stocastica che corrisponde alla dinamica di Glauber a temperatura zero per il modello di Ising. Un problema classico e' quello di stimare il tempo (mixing time) che la dinamica richiede per raggiungere l'equilibrio (la misura uniforme). La congettura, basata sull'idea euristica che l'interfaccia evolve seguendo un'equazione di tipo "movimento per curvatura media", e' che il mixing time cresca essenzialmente come il quadrato del diametro della regione U. Il nostro risultato principale e' una prova di questa congettura, sotto l'ipotesi che la forma macroscopica non presenti singolarita'. Basato su lavori in collaborazione con P. Caputo, B. Laslier e F. Martinelli.

1 0

Mercati Energetici e Metodi Quantitativi - edizione 2014
by Tiziano Vargiolu 21 Feb '14

21 Feb '14

Buongiorno, volevamo informarti che anche quest'anno si ripeter? il workshop "Mercati Energetici e Metodi Quantitativi: un Ponte tra Universit? e Aziende". Trovi tutte le informazioni sul sito web http://www.unponte2014.stat.unipd.it/ Sono aperte le submission per gli speaker (accademici e professionisti provenienti da aziende) che desiderino presentare un talk. Inoltre, quest'anno abbiamo deciso di estendere l'iniziativa organizzando, nei due giorni precedenti la conferenza, quattro tutorial sui seguenti argomenti: - Introduzione ai mercati dell'energia e del gas - Rischio di credito e di controparte nei mercati energetici - Strumenti di analisi e di previsione per i mercati energetici. - Tecniche di gestione di portafoglio e di ottimizzazione: i contratti strutturati nei mercati dell'energia. Tutte le informazioni sui tutorial si trovano alla pagina http://events.math.unipd.it/memq2014/ In attesa di rincontrarci a Padova, porgiamo i nostri pi? Cordiali Saluti, gli Organizzatori Giorgia Callegaro Enrico Edoli Francesco Lisi Tiziano Vargiolu

1 0

ABS14- APPLIED BAYESIAN NONPARAMETRICS
by raffaele argiento 21 Feb '14

21 Feb '14

Registration is now open for *ABS14*, the 2014 edition of the Applied Bayesian Statistics School, which has been running since 2004. The topic of this year is *APPLIED BAYESIAN NONPARAMETRICS*. The lecturers will be Michael JORDAN (Berkeley) and Francois CARON (Oxford). The school will be held at Villa del Grumello, Como, Italy, from June 16 till 20, 2014. The school webpage is www.mi.imati.cnr.it/conferences/abs14.html Please note that a very limited number of participants (35) will be admitted. There is a late registration fee after April, 1st. For information please contact abs14(a)mi.imati.cnr.it Best regards, Raffaele Argiento Executive director of ABS14 -- Dr Raffaele Argiento CNR IMATI -- Milano Tel. +39 02 23699.529 Web www.mi.imati.cnr.it/raffaele

1 0

University of Kent-PhD Scholarship
by Fabrizio Leisen 20 Feb '14

20 Feb '14

Con preghiera di diffusione. Aggiungo che la borsa partirebbe da Settembre 2014. Cordiali Saluti, Fabrizio Leisen Postgraduate Scholarship Non-parametric priors for Bayesian inference *University* *of* *Kent* School of Mathematics, Statistics and Actuarial Science *Project:** Non-parametric priors for Bayesian Inference* *Supervisor:** Fabrizio Leisen* The use of Bayesian non-parametric (BNP) priors in applied statistical modelling has become increasingly popular in the last few years. From the seminal paper of Ferguson (1973, Annals of Statistics), the Dirichlet Process and its extensions have been increasingly used to address inferential problems in many fields. Examples range from variable selection in genetics to linguistics, psychology, human learning, image segmentation and applications to the neurosciences. The project aims to introduce and/or investigate new Bayesian non-parametric priors that can be used to describe a wide spectrum of phenomena. Keywords include: - Dirichlet and Pitman Yor Processes - Vectors of Dependent random probability measures - Non-exchangeable species sampling sequences *The* *School* *of* *Mathematics,* *Statistics* *and* *Actuarial* *Science* The School offers a lively research culture with a thriving group of around 250 taught postgraduates students and almost 100 postgraduate students, postdoctoral researchers and academic staff. Kent is among the best research-intensive universities in the UK. In the 2008 Research Assessment Exercise (RAE), the university was ranked 24th out of 159 institutions for its world-leading research, with six of our subject areas (including statistics) in the top tennationwide. Details of the research undertaken by the School can be found at: http://www.kent.ac.uk/smsas/postgraduate/phd-applications.html *The* *funding* This scholarship is partially funded by the FP7 Marie Curie Career Integration Grant "Flexible Bayesian non-parametric priors" held by Fabrizio Leisen. The scholarship is offered at the standard UK Research Councils' rate (currently£13,863) and will cover the tuition fees for a period of 3.5 years subject to satisfactory progress at each review period. *Entry* *Requirements* All candidates must have an excellent academic track record in Mathematics or Statistics or related disciplines and hold a good Honours degree in a relevant subject or equivalent. A Masters qualification such as an MSc or MMath orresearch experience would be advantageous. *To* *apply* To apply complete the online application form available by clicking the *'Apply'* button below or by visiting: http://www.kent.ac.uk/studying/postgrad/apply/index.html and select School research Scholarship under `How are you intendingto fund your studies?' and mention this research project in the research proposal. Closing date: 31st March 2014. -- Fabrizio Leisen Senior Lecturer in Statistics School of Mathematics, Statistics and Actuarial Sciences Cornwallis Building, University of Kent, Canterbury, CT2 7NF http://sites.google.com/site/fabrizioleisen/

1 0

de Finetti Risk Seminar - febbraio 2014
by Emanuela Rosazza Gianin 20 Feb '14

20 Feb '14

On behalf of the Scientific Committee of The de Finetti Risk Seminars - on the Mathematical Theory of Economics and Finance in Milano, we are glad to invite you to participate at the "de Finetti Risk Seminar" on February 26, 2014 at 18.00 with the Lecture Evaluation of long-dated investments under uncertain growth trend, volatility, and catastrophes CHRISTIAN GOLLIER Toulouse School of Economics LOCATION: The seminar will be held on Wedsnesday, February 26, at 18.00 at room 3-E4-SR03, Bocconi University, Via Roentgen 1, Milano. A refreshment will be offered at 17.30. Scientific Committee: Prof. Marco Frittelli (Univ. degli Studi di Milano) Prof. Fabio Maccheroni (Univ. Bocconi) Prof. Massimo Marinacci (Univ. Bocconi) Prof. Emanuela Rosazza Gianin (Univ. Milano-Bicocca) Dott. Simone Cerreia-Voglio (Univ. Bocconi) Dott. Marco Maggis (Univ. degli Studi di Milano) ******************************************************************************************* Emanuela Rosazza Gianin Dipartimento di Metodi Quantitativi per le Scienze Economiche ed Aziendali Università di Milano Bicocca Edificio U7 - 4° Piano Via Bicocca degli Arcimboldi, 8 20126 Milano Tel. 02 64483208 Fax. 02 64483105 e-mail: emanuela.rosazza1(a)unimib.it *******************************************************************************************

1 0

Avviso di seminario :: Mortera@DSS (Scienze Statistiche, Sapienza)
by Pierpaolo Brutti 17 Feb '14

17 Feb '14

----------------------------------------------------------------------------- A v v i s o d i S e m i n a r i o ----------------------------------------------------------------------------- Venerdì 21 Febbraio, ore 11am ----------------------------------------------------------------------------- Stanza 34 Dipartimento di Scienze Statistiche Sapienza Università di Roma JULIA MORTERA (Fac. di Economia, Università degli Studi di Roma3) terrà un seminario dal titolo ANALYSIS OF FORENSIC DNA MIXTURES tutti gli interessati sono invitati a partecipare. ----------------------------------------------------------------------------- Maggiori informazioni sui seminari presso il DSS sono consultabili a quest'indirizzo: http://goo.gl/Y6OQYm Saluti Pierpaolo Brutti - Fulvio De Santis --- Summary DNA is now routinely used in criminal investigations and court cases, although DNA samples taken at crime scenes are of varying quality and therefore present challenging problems for their interpretation. We present a statistical model for the quantitative peak information obtained from an electropherogram (EPG) of a forensic DNA sample and illustrate its potential use for the analysis of criminal cases. In contrast to most previously used methods, we directly model the peak height information and incorporates important artefacts associated with the production of the EPG. Our model has a number of unknown parameters, and we show that these can be estimated by the method of maximum likelihood in the presence of multiple unknown contributors, and their approximate standard errors calculated; the computations exploit a Bayesian network representation of the model. A case example from a UK trial, as reported in the literature, is used to illustrate the efficacy and use of the model, both in finding likelihood ratios to quantify the strength of evidence, and in the deconvolution of mixtures for the purpose of finding likely profiles of one or more unknown contributors to a DNA sample. Our model is readily extended to simultaneous analysis of more than one mixture as illustrated in a case example. We show that combination of evidence from several samples may give an evidential strength close to that of a single source trace and thus modelling of peak height information provides for a potentially very efficient mixture analysis. Joint work with Robert Cowell, Therese Graversen and Steffen Lauritzen

1 0

Research fellowship at the Insitute of Economics, Scuola Sant'Anna Pisa
by Enrico Scalas 17 Feb '14

17 Feb '14

Car* collegh*, mi hanno segnalato questa posizione post-dottorale presso Economia al Sant'Anna: http://www.sssup.it/context_elenco.jsp?ID_LINK=12550&area=6&id_context=44264 Cercano una persona che ben conosca probabilita' e teoria dei processi stocastici e, eventualmente, e' gradita una formazione in finanza. Per ulteriori infomazioni si puo' scrivere al Prof. Giulio Bottazzi: g.bottazzi(a)sssup.it Per favore, fate circolare il link alle persone interessate che conoscete. Cordiali saluti, Enrico Scalas Professor of Statistics and Probability University of Sussex http://www.sussex.ac.uk/maths/people/peoplelists/person/330303

1 0

1 posto di Maitre de Conferences e 1 di Professore in Probabilita' all'Universite' Lyon 1
by Fabio Toninelli 17 Feb '14

17 Feb '14

Gentili colleghi all'Universita' Lyon 1 e' aperto un concorso per un posto di Maitre de Conferences in probabilità e per un posto di Professore in Probabilita' (inizio: 1 settembre 2014). Entrambe le posizioni sono permanenti. Il profilo scientifico e' largo, http://math.univ-lyon1.fr/recrutements/profils_14/MCF_P_en.pdf e http://math.univ-lyon1.fr/recrutements/profils_14/PR_en.pdf. I temi di ricerca del gruppo di probabilità' di Lyon 1 sono descritti qui: http://math.univ-lyon1.fr/icj/?option=theme&th=5 I candidati interessati devono spedire elettronicamente il loro dossier ENTRO IL 12 MARZO 2014, tramite il sito https://galaxie.enseignementsup-recherche.gouv.fr/antares/can/index.jsp Qualche consiglio su come comporre il dossier di candidatura si trova qui: http://postes.smai.emath.fr/2014/OUTILS/conseils/index.php#it2 Attenzione: Il concorso e' aperto ai i candidati che hanno gia' passato la procedura di "Qualification" nazionale francese, oppure che hanno attualmente all'estero una posizione di livello equivalente a quelle di Maitre de Conferences o di Professore. Per ulteriori informazioni sullo svolgimento del concorso, i candidati interessati possono contattare o me (toninelli(a)math.univ-lyon1.fr) o Christophe Sabot (sabot(a)math.univ-lyon1.fr) Cordiali saluti Fabio Toninelli Institut Camille Jordan, Universite' Lyon 1 43 bd du 11 novembre 1918 69622 Villeurbanne Cedex, France Office 105, tel: +33 (0) 4 26 23 44 41

1 0

Fwd: Saint-Flour 2014
by Marco Romito 17 Feb '14

17 Feb '14

SAINT-FLOUR 2014 - SECOND ANNOUNCEMENT Dear colleagues, Online registration is now open for the 44th Saint-Flour Probability summer school, which will be held on July 15-25. Please note the DEADLINE FOR REGISTRATION: APRIL 18 This year, the courses are: Martin HAIRER : Regularity structures Gregory MIERMONT : Aspects of random maps SPECIAL NOTICE The previously announced lecture by Sourav Chatterjee is postponed to 2015. Consequently, this year's school will feature only two courses, and its length is slightly reduced. The registration form as well as some useful information about the school can be found on the web pages: http://math.univ-bpclermont.fr/stflour/index.php (in French) http://math.univ-bpclermont.fr/stflour/stflour-en.php (in English) For registration, you will have to accept the security certificate in your browser. These pages also contain the advertisement poster of the school (in French or in English). It would be helpful for us if you could print it and post it in your department. Thank you. Please forward the above information to anyone who might be interested. Best regards, The organizing committee Christophe Bahadoran, Arnaud Guillin, Laurent Serlet stflour(a)math.univ-bpclermont.fr Laboratoire de Mathématiques CNRS UMR 6620 Université Blaise Pascal (Clermont-Ferrand 2) Complexe Universitaire des Cézeaux BP80026 F-63177 Aubière tel (+33) 4 73 40 70 50 fax (+33)4 73 40 54 50

1 0

Seminario CHOPIN
by Matteo Ruggiero 14 Feb '14

14 Feb '14

**************************************************************** STATISTICS SEMINARS @ COLLEGIO CARLO ALBERTO **************************************************************** Venerdi' 21 Febbraio 2014 alle ore 12:00, presso la sala rossa del Collegio Carlo Alberto, Moncalieri (TO), si terra' il seguente seminario: Nicolas CHOPIN (ENSAE, France) SEQUENTIAL QUASI MONTE CARLO Abstract: We develop a new class of algorithms, SQMC (Sequential Quasi Monte Carlo), as a variant of SMC (Sequential Monte Carlo) based on low-discrepancy points. The complexity of SQMC is O(N log N) where N is the number of simulations at each iteration, and its error rate is smaller than the Monte Carlo rate O(N^{-1/2}). The only requirement to implement SQMC is the ability to write the simulation of particle x_t^n given x_{t-1}^n as a deterministic function of x_{t-1}^n and uniform variates. We show that SQMC is amenable to the same extensions as standard SMC, such as forward smoothing, backward smoothing, unbiased likelihood evaluation, and so on. In particular, SQMC may replace SMC within a PMCMC (particle Markov chain Monte Carlo) algorithm. We establish several convergence results. We provide numerical evidence in several difficult scenarios than SQMC significantly outperforms SMC in terms of approximation error. Joint work with Mathieu Gerber. Tutti gli interessati sono invitati a partecipare. Il seminario e' organizzato dalla "de Castro" Statistics Initiative (http://www.carloalberto.org/stats) in collaborazione con il Collegio Carlo Alberto. Cordiali saluti, Matteo Ruggiero --------- Matteo Ruggiero University of Torino & Collegio Carlo Alberto http://web.econ.unito.it/ruggiero

1 0