- Random - Mailing list — Dipartimento di Matematica, UniPI

Scuola ABS a Genova (3-6/6/25): Spatio-temporal Methods in Environmental Epidemiology
by Fabrizio Ruggeri 23 Apr '25

23 Apr '25

The ABS (Applied Bayesian Statistics) schools have been organised by CNR-IMATI (Italian National Research Council - Institute of Applied Mathematics and Information Technologies, Milano Department) since 2004, inviting top researchers and combining lectures with practical sessions and informal discussions about participants' projects. Some seats are still available for the ABS25 summer school in Genova (Italy), 3-6 June 2025. Reduced fees are available until 11 May 2025. TOPIC: Spatio-temporal Methods in Environmental Epidemiology WEBSITE: https://abs25.imati.cnr.it/ DETAILED PROGRAMME: https://abs25.imati.cnr.it/programme.htm CONTACT: abs25(a)mi.imati.cnr.it LECTURERS: Alexandra Schmidt (McGill University, Canada) and (practical sessions) Carlo Zaccardi (Università di Chieti-Pescara, Italy) ALEXANDRA SCHMIDT (B.Sc. and M.Sc. Rio de Janeiro, Ph.D. Sheffield) is Professor of Biostatistics and helds the endowed University Chair in the Department of Epidemiology, Biostatistics and Occupational Health at McGill University. Between 2002 and 2016 she worked in the Department of Statistical Methods of the Federal University of Rio de Janeiro, Brazil, where she became Full Professor of Statistics in 2012. She is an Elected Fellow of the International Society for Bayesian Analysis (2024), the American Statistical Association (2020) and an Elected Member of the International Statistical Institute (2010). She was awarded the Distinguished Achievement Medal (2017) from the American Statistical Association’s Section on Statistics and the Environmentand the Abdel El-Shaarawi Young Investigator Award (2008) from The International Environmetrics Society. She was the President of the International Society for Bayesian Analysis in 2015. Currently, she is the Program Chair of the 2025 Joint Statistical Meetings in Nashville, USA, and Council Member of the International Statistical Institute. More details on Prof. Schmidt (including publications, mostly on the topic of the course) at https://alex-schmidt.research.mcgill.ca/ CARLO ZACCARDI got his B.Sc., M.Sc., Ph.D. Università di Chieti-Pescara, where he is currently post-doc. GENOVA: Information on what to do and see at https://www.visitgenoa.it/en Best regards, Elisa Varini and Fabrizio Ruggeri (ABS25 Executive Director and Director) ---------------------------- Fabrizio Ruggeri President-Elect (2023-2025) CNR IMATI International Statistical Institute Via Alfonso Corti 12 fabrizio(a)mi.imati.cnr.it I-20133 Milano (Italy) www.mi.imati.cnr.it/fabrizio

1 0

Reminder: OWABI - Ayush Bharti - April 24
by Massimiliano Tamborrino 23 Apr '25

23 Apr '25

Dear all, a kind reminder of tomorrow's (Thursday the 24th April, 11am UK time) OWABI seminar<http://www.warwick.ac.uk/oneworldabc> by Ayush Bharti (Aalto University), who will talk about "Cost-aware simulation-based inference ", with an abstract reported below. The talk will be exceptionally streamed on Zoom https://chalmers.zoom.us/j/67207457257 (password 201659), Abstract: Simulation-based inference (SBI) is the preferred framework for estimating parameters of intractable models in science and engineering. A significant challenge in this context is the large computational cost of simulating data from complex models, and the fact that this cost often depends on parameter values. We therefore propose cost-aware SBI methods which can significantly reduce the cost of existing sampling-based SBI methods, such as neural SBI and approximate Bayesian computation. This is achieved through a combination of rejection and self-normalised importance sampling, which significantly reduces the number of expensive simulations needed. Our approach is studied extensively on models from epidemiology to telecommunications engineering, where we obtain significant reductions in the overall cost of inference. Keywords: simulation-based inference, approximate Bayesian computation, neural posterior estimation, neural likelihood estimation, importance sampling Best, Massimiliano on the behalf of the OWABI Organisers ------ Dr. Massimiliano Tamborrino Reader (Associate Professor) and WIHEA Fellow Department of Statistics University of Warwick https://warwick.ac.uk/tamborrino

1 0

PhD in Economics and Finance, University of Verona - Call for Applications
by Athena Picarelli 22 Apr '25

22 Apr '25

Dear colleagues, We are pleased to announce the 2025 call for applications of the PhD Program in Economics and Finance at the University of Verona. The Program offers two dedicated tracks: “Economics” and “Mathematics and Data Analytics for Finance”. It aims at bringing brilliant students to the international research frontier, and at developing their ability to create their own research contributions. This year six positions are available: five with full scholarships (about 1,600 euros per month) and one without scholarship. We invite applications from outstanding graduates who hold or are expected to hold a master’s degree in Economics, Finance or related fields. The following material is required for an application: i) Certificate with final graduation mark or transcript with exam grades; ii) Curriculum Vitae; iii) Original research proposal of maximum 2,000 words; iv) Two reference letters; v) Further documents the candidate considers relevant for the evaluation. Here is the link to the application page: https://www.corsi.univr.it/?ent=cs&id=1008&menu=iscriversi&tab=comeiscriver… *The deadline for the application is May 20, 2025.* *Description of the Program* The PhD Program in Economics and Finance of the University of Verona trains academic and professional figures able to autonomously carry out research in economics and finance at universities, research institutes, consulting firms, public and private companies. PhD graduates undertake job positions requiring critical and problem solving skills, in which to matter are the ability to identify a problem and analyze it using economic reasoning, manage and process data through a statistical approach, interpret the findings and communicate results and implications. The four-year PhD Program in Economics and Finance consists of a course-work part and a research part. During the first part of the program, students attend advanced courses (both compulsory and elective) related to their chosen track (“Economics” or “Mathematics and Data Analytics for Finance”). Students then develop an independent study and research agenda under the guidance of two supervisors. The program is completed by the final thesis containing research contributions following high-quality international standards. Our PhD Program also offers personal research funds, access to dedicated room and Department facilities, and financial support for study and research periods in foreign universities or institutions. The University of Verona is among the top hundred world universities with less than 50 years in the rankings of the Times Higher Education. In the RepEc ranking, the Department of Economics ranks in the top 10% of the Italian distribution and in the top 25% of the world distribution of research departments and institutions in Economics. It received the “Department of Excellence 2023-2027” seal by the Italian ministry of university and research. For further information please visit the official Program webpage, https://www.corsi.univr.it/?ent=cs&id=1008&menu=ilcorso&tab=presentazione lang=en <https://www.corsi.univr.it/?ent=cs&id=1008&menu=ilcorso&tab=presentazione&l…> or contact the program coordinator, Prof. Athena Picarelli ( athena.picarelli(a)univr.it) -------------------- -- *Athena Picarelli* Professor Coordinator of the PhD program in Economics and Finance Dipartimento di Scienze Economiche Università di Verona Polo Santa Marta, Verona.

1 0

Conference in CIRM, Marseille in October 2025: New trends of Stochastic nonlinear systems
by Erika Hausenblas 22 Apr '25

22 Apr '25

We would like to bring to your attention the conference in CIRM - Lumini, Marseille from 20 – 24 October, 2025: New trends of stochastic nonlinear systems: well-posedeness, dynamics and numerics Erika Hausenblas (University of Leoben) Chengcheng Ling (University of Augsburg) Stéphane Menozzi (Université d’Évry) https://conferences.cirm-math.fr/3374.html Stochastic analysis is a very dynamic field which has undergone numerous developments over the last decades: stochastic differential equations (SDE), stochastic partial differential equations (EDPS), Malliavin calculus... In order to study new singular complex models, which in particular arise from regularization/de-regulation by noise-related problems, particle systems, quantum mechanics or machine learning, new ideas have appeared, yielding numerous results concerning the well-posedness, dynamics and approximation of singular ED(P)S in numerous scientific or engineering fields. Among these ideas, we can mention: the application of convex integration techniques for stochastic equations, the sewing lemma to highlight fine regularisation properties of the underlying noise, quantum field theory to help understand quantum dynamics, or the association of classical techniques with tools such as rough paths theory to solve problems which could not be addressed independently. If you would like to participate, please contact one of the organisers or spdescirmmarseille(a)gmail.com.

1 0

I: PhD a Singapore
by Federico Sau 22 Apr '25

22 Apr '25

Buongiorno a tutti, Ricevo e inoltro l'apertura di posizioni di dottorato a Singapore (NUS) con Matteo Mucciconi https://matteomucciconi.github.io/. I programmi partono a gennaio 2026 (deadline il 15 maggio) o ad agosto 2026 (deadline il 15 novembre). Cordiali saluti, Federico ________________________________ Da: Matteo Mucciconi Inviato: Martedì, 22 Aprile, 2025 09:21 A: Federico Sau Oggetto: PhD a Singapore Ciao Federico, spero tu stia bene. Ad Agosto dell'anno scorso ci siamo incontrati qui a Singapore e ti avevo parlato del fatto che volevo promuovere posizioni di PhD qui ad NUS. Se conosci degli studenti che potrebbero essere interessati a fare un PhD qui, potresti far girare questo pamphlet, o dare loro il mio contatto? I programmi partono da Gennaio 2026 (deadline il 15 Maggio) o Agosto 2026 (deadline il 15 Novembre). Ti ringrazio in anticipo del supporto. Matteo

1 0

Tom Kurtz
by c.costantini＠unich.it 22 Apr '25

22 Apr '25

E' con grande tristezza che do l'annuncio della morte, sabato 19 aprile, di Tom Kurtz. Tom ha visitato l'Italia molte volte e molti probabilisti italiani l'hanno conosciuto di persona. Il libro che Tom ha scritto nel 1986 insieme a Stewart Ethier, "Markov processes: characterization and convergence", è tuttora un testo di riferimento. Tom ha scritto anche un altro libro, con Jin Feng, su "Large deviations for stochastic processes". Tom ha dato importantissimi contributi non solo sulla caratterizzazione dei processi di Markov e sui metodi per studiarne la convergenza, e sulla teoria delle grandi deviazioni, ma anche alla teoria del filtraggio, alla teoria dei processi a valori misura, allo studio delle equazioni differenziali stocastiche alle derivate parziali, allo studio dei processi di punto spaziali, alla dinamica delle popolazioni, alla teoria delle diffusioni riflettenti, alla teoria delle reti stocastiche, in particolare per le reazioni chimiche, e in altri campi ancora. Caratteristica di Tom era la sua disponibilità a parlare con tutti, da un collega a un giovanissimo studente, condividendo con grandissima generosità il suo tempo, la sua conoscenza e le sue idee. Cristina Costantini

1 0

Seminario PRISMA lunedì 5 maggio 2025 - C. Orrieri & L. Scarpa
by Sonia Mazzucchi 22 Apr '25

22 Apr '25

Seminari on-line del gruppo UMI - PRISMA (http://www.umi-prisma.polito.it/) I seminari PRISMA hanno un formato di "colloquium" per creare un'occasione di scambio e discussione con tutta la comunità dei probabilisti e statistici italiani. Ogni giornata comprende due relatori che tengono due seminari di 30 minuti strettamente connessi, per presentare alla comunità una prospettiva sul proprio ambito di ricerca. Da quest'anno le registrazioni dei seminari vengono pubblicate sul canale YouTube dell'UMI: https://youtube.com/playlist?list=PLmySpc-jrtAMq84VH71evyqPc1hl6eEQb Il prossimo appuntamento è per *lunedì 5 maggio 2025*. I relatori saranno *Carlo Orrieri* (Università di Pavia) e *Luca Scarpa* (Politecnico di Milano) che parleranno di: *Equazioni stocastiche doppiamente nonlineari e relativi problemi di regolarizzazione per rumore* con il seguente orario: 16:00 Primo seminario 16:30 Pausa e discussione 16:45 Secondo seminario 17:15 Conclusione e discussione Trovate di seguito il riassunto. I seminari verranno trasmessi via Zoom al seguente link: https://unitn.zoom.us/j/88514293418 ID riunione: 885 1429 3418 Codice d’accesso: 236100 Vi aspettiamo numerosi! Alberto Chiarini e Sonia Mazzucchi %%%%%%%%%%%%%%%%%%%%%%%%%%%% RELATORI: Carlo Orrieri (Università di Pavia) e Luca Scarpa (Politecnico di Milano) TITOLO: Equazioni stocastiche doppiamente nonlineari e relativi problemi di regolarizzazione per rumore RIASSUNTO: Nella prima parte del seminario verranno introdotte alcune classi di equazioni di evoluzione in relazione alla modellizzazione di problemi di transizione di fase. Dal punto di vista matematico tali equazioni sono caratterizzate da una dinamica doppiamente nonlineare che tipicamente non ne assicura la buona positura. In particolare, l’unicità delle soluzioni viene a mancare. Questo motiva l’introduzione e l'analisi di opportune formulazioni stocastiche per tali modelli, nell’ottica di ottenere effetti di regolarizzazione per rumore. Nella seconda parte il problema di regolarizzazione per rumore verrà inquadrato nel contesto più generale di equazioni di evoluzione stocastiche con drift singolare e verranno presentati alcuni risultati di unicità. L'applicabilità di tali tecniche identificherà naturalmente un concetto di criticità che porrà le equazioni doppiamente nonlineari in un regime supercritico. Per queste verrà fornito infine un risultato parziale di stabilità per rumore. I risultati presentati nei seminari sono stati ottenuti in collaborazione con F. Bertacco (Imperial College London) e U. Stefanelli (Università di Vienna). %%%%%%%%%%%%%%%%%%%%%%%%%%%%

1 0

[summer school] PrefStat 2025 in Oslo: schedule announced & early-bird extended
by Valeria Vitelli 16 Apr '25

16 Apr '25

Dear all, A *tentative schedule* for the PrefStat summer school 2025 is now announced! Find out more here <https://www.prefstat.org/schedule/>. *Early-bird registration deadline* is now also postponed to **** April 30th, 2025 **** *Preference Statistics summer school* Detailed information on the website <https://www.integreat.no/events/public-events/workshops/prefstat-summer-sch…> Dates: *June 30th - July 4th, 2025* Place: Blindern, *University of Oslo*, Niels Henrik Abels building *Target audience* Researchers in the area of data science, machine learning, statistics, and related fields. Master students with basic skills in machine learning and statistics are also welcome. PrefStat aims to provide participants with a solid foundation in preference learning, and to equip them with the skills and knowledge necessary to apply these methods to real-world problems. *Course description* The PrefStat summer school is a high-level course on cutting-edge topics in the specific context of Statistical Learning from Preference Information, or Preference Learning. The course is designed to provide a comprehensive overview of preference statistics, a rapidly growing field that has gained significant attention in recent years due to the numerous application fields involving human preferences: recommender systems, Large Language Models, surveys and psychological experiments, marketing, economics, and political science. Preference learning is concerned with all data analyses involving preferences, rankings, ratings, clicking, or any kind of ordinal data. It entails modeling experiments involving a set of assessors (experts, judges, users) who express order relations about a set of items, thus being a subfield of both supervised and unsupervised statistical learning. The school provides a deep introduction to the topic and insight into more challenging tasks that are of interest in modern applications, such as handling partial, unstructured, exogenous information, individual preference prediction, and importance feature selection. PrefStat 2025 combines lectures delivered by internationally leading scholars on the specific designated topic and supervised practical tutorials. Feel free to contact us (ccied) for inquiries. We are happy to welcome you to Oslo in June! Warm regards and Happy Easter, Valeria -- Valeria Vitelli Oslo Centre for Biostatistics and Epidemiology, Department of Biostatistics, University of Oslo, Norway group page: https://www.med.uio.no/imb/english/research/groups/statistics-high-dimensio… <https://www.med.uio.no/imb/english/research/groups/statistics-high-dimensio…> mailto: valeria.vitelli(a)medisin.uio.no

1 0

OWABI - Ayush Bharti - April 24
by Massimiliano Tamborrino 15 Apr '25

15 Apr '25

Dear all, the next OWABI seminar<http://www.warwick.ac.uk/oneworldabc> is scheduled on Thursday the 24th April at 11am UK time. Our next speaker is Ayush Bharti (Aalto University), who will talk about "Cost-aware simulation-based inference ", with an abstract reported below. The talk will be exceptionally streamed on Zoom https://chalmers.zoom.us/j/67207457257 (password 201659), Abstract: Simulation-based inference (SBI) is the preferred framework for estimating parameters of intractable models in science and engineering. A significant challenge in this context is the large computational cost of simulating data from complex models, and the fact that this cost often depends on parameter values. We therefore propose cost-aware SBI methods which can significantly reduce the cost of existing sampling-based SBI methods, such as neural SBI and approximate Bayesian computation. This is achieved through a combination of rejection and self-normalised importance sampling, which significantly reduces the number of expensive simulations needed. Our approach is studied extensively on models from epidemiology to telecommunications engineering, where we obtain significant reductions in the overall cost of inference. Keywords: simulation-based inference, approximate Bayesian computation, neural posterior estimation, neural likelihood estimation, importance sampling In the meantime, enjoy the Easter break. Best, Massimiliano on the behalf of the OWABI Organisers ------ Dr. Massimiliano Tamborrino Reader (Associate Professor) and WIHEA Fellow Department of Statistics University of Warwick https://warwick.ac.uk/tamborrino

1 0

Fwd: Corso su biliardi a Cortona, 29 giugno - 4 luglio 2025
by Elisabetta Candellero 14 Apr '25

14 Apr '25

Ricevo e inoltro volentieri: *Dal 29 giugno al 4 luglio la Scuola Matematica Interuniversitaria organizza al Palazzone di Cortona un corso su dinamica dei biliardi, tenuto da Chris Burdzy e Marco Lenci. Il termine delle iscrizioni e' a fine aprile. I candidati ammessi vengono ospitati al Palazzone.* Piu' informazioni sono reperibili al seguente link: https://www.smi-math.unipr.it/cortona/30/ . Elisabetta

1 0