- Random - Mailing list — Dipartimento di Matematica, UniPI

Seminar in Statistics GONZALO MENA
by Pierpaolo De Blasi 22 Nov '21

22 Nov '21

SEMINARS IN STATISTICS @ COLLEGIO CARLO ALBERTO <https://www.carloalberto.org/events/category/seminars/seminars-in-statistic…> Venerdi 26 Novembre 2021, alle ore 12.00, presso il Collegio Carlo Alberto, in Piazza Arbarello 8, Torino, si terrà il seguente seminario: ------------------------------------------------ Speaker: *Gonzalo Mena *(University of Oxford) Title: *On the unreasonable effectiveness of Sinkhorn algorithm for learning permutations and entropic optimal transport* Abstract: Sinkhorn's algorithm realizes the solution of entropy-regularized linear programs on certain matrix polytopes. In the past years, the interest in this algorithm has grown considerably because of its usefulness as a tool for the modeling of permutations, and because of its fundamental role in the solution of an entropic optimal transport problem, also called the Schrödinger bridge. In this talk, I will give an overview of my work in relation to these two areas. First, regarding entropic optimal transport, I will argue that this tool is valuable for deriving sensible statistical procedures. Indeed, we show that it enjoys a substantially better sample complexity compared to optimal transport, which suffers from the curse of dimensionality. Also, in the more applied setup of model-based clustering we show that it can be used as an alternative to the log-likelihood, since it has fewer bad local optima. Based on this observation, we develop a new algorithm, Sinkhorn-EM, in which we only modify the E-step to solve an Entropic Optimal Transport problem. Our algorithm is shown to attain better practical performance. Second, regarding permutations, I will describe some successful applications in Deep Learning, and in neuroscience, for the inference of neural identities in C.elegans worms. Links https://arxiv.org/abs/1802.08665 https://arxiv.org/abs/1905.11882 https://arxiv.org/abs/2006.16548 ------------------------------------------------ In ottemperanza alle norme anti Covid, per partecipare in presenza è necessario prenotarsi tramite il seguente form online: https://forms.gle/XyyJ3JaqTeZLi92A6 Sarà possibile seguire il seminario anche in streaming: Join Zoom Meeting <https://us02web.zoom.us/j/84926221121?pwd=eDdycEV3M2VVVU1FSEszM000eDlIdz09> Meeting ID: 849 2622 1121 Passcode: 899297 Il seminario è organizzato dalla "de Castro" Statistics Initiative www.carloalberto.org/stats Cordiali saluti, Pierpaolo De Blasi --- University of Torino & Collegio Carlo Alberto carloalberto.org/pdeblasi <https://sites.google.com/a/carloalberto.org/pdeblasi/>

1 0

One World ABC Seminar - Clara Grazian - November 25
by Massimiliano ... 22 Nov '21

22 Nov '21

Dear all, it is our pleasure to invite you to a new talk of the One WorldABC Seminar<https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwarwick.…>. Our next speaker will be Clara Grazian<https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fresearch…>, who will talk about PET-ABC: A Bayesian likelihood free tool for kinetic models<https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fiopscien…>, on Thursday November 25, at 11.30am UK time, with an abstract reported below. To join the talk, please click on the Zoom link below https://chalmers.zoom.us/j/65793605413<https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fchalmers…> Password: 810265 If you are interested in presenting your work on ABC and likelihood-free methods in the new year, please get in touch with one of the organisers. If you miss last talk by Michael Gutmann, you can access its recording here https://www.youtube.com/watch?v=oUD6mPttyw4&feature=youtu.be<https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.yout…> We look forward to seeing you on Thursday, best wishes, Massimiliano on the behalf of the One World ABC Seminar Organisers. --- When: Thursday, November 25, 11.30am UK Time Speaker: Clara Grazian<https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fresearch…>, UNSW Sidney Title: PET-ABC: A Bayesian likelihood free tool for kinetic models Abstract: We describe an intuitive, easy to use method called PET-ABC that enables full Bayesian statistical inference from single subject dynamic PET data. The performance of PET-ABC was compared with weighted non-linear least squares (WNLS) in terms of reliability of kinetic parameter estimation and statistical power for model selection. Dynamic PET data based on 1-tissue and 2-tissue compartmental models were simulated with 2 noise models and 3 noise levels. PET-ABC was used to evaluate the reliability of parameter estimates under each condition. It was also used to perform model selection for a simulated noisy dataset composed of a mixture of 1- and 2-tissue compartment kinetics. Finally, PET-ABC was used to analyze a non-steady state dynamic study performed on a fully conscious rat administered either 2 mg.kg-1 amphetamine or saline 20 min after tracer injection. Reference: Y. Fan, G. Emvalomenos, C. Grazian, S. R. Meikle, PET-ABC: fully Bayesian likelihood-free inference for kinetic models<https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fiopscien…>, Physics in Medicine and Biology, 66 (11), 115002, 2021. ------ Dr. Massimiliano Tamborrino Assistant Professor Department of Statistics University of Warwick https://warwick.ac.uk/tamborrino<https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwarwick.…>

1 0

2022 PIMS-CRM Summer School in Probability
by Faggionato, Alessandra 22 Nov '21

22 Nov '21

Buongiorno, ricevo da Omer Angel ed inoltro volentieri. Saluti Alessandra Faggionato %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Dear colleague, The 2022 PIMS-CRM Summer School in Probability will be held at the University of British Columbia from May 30 to June 24, 2022. This month-long program, originally planned for 2020, is especially appropriate for young researchers in probability, although others may of course attend. While there is still uncertainty stemming from covid regarding travel and conferences, we are hopeful that the school will be able to run this summer. The main courses will be given by Ivan Corwin (Columbia University), and Frank den Hollander (University of Leiden). Their respective titles are Interacting particle systems, growth models, stochastic PDEs and directed polymers through the lens of the stochastic six vertex model and Metastability for interacting particle systems Three 3-hour mini courses will be given by Paul Bourgade, Jean-Francois Le Gall and Nike Sun. There will also be an opportunity for some participants to give short talks on their own research. More information about the program may be found on the School's website at http://www.math.ubc.ca/Links/ssprob22 Graduate students and postdoctoral fellows who will attend the entire summer school can apply for financial support for on-campus accommodation through mathjobs: https://www.mathjobs.org/jobs/list/18950 Major support for the conference has been provided by PIMS, CRM, NSF, and the Department of Mathematics at UBC. Questions can be directed to one of the UBC organizers listed below. Please forward this email to students and postdocs who may be interested in attending. Sincerely, Louigi Addario-Berry <louigi.addario(a)mcgill.ca> Omer Angel <angel(a)math.ubc.ca> Jonathan Hermon <jhermon(a)math.ubc.ca> Mathav Murugan <mathav(a)math.ubc.ca> Gordon Slade <slade(a)math.ubc.ca>

1 0

Mini-workshop Optimal Transport and Uncertainty, 2:30 pm Friday 26 Nov 2021
by Dario Trevisan 21 Nov '21

21 Nov '21

Cari tutti, segnalo il miniworkshop "Optimal Transport and Uncertainty" che si terrà il pomeriggio di venerdì 26/11/2021, a partire dalle ore 14:30, presso l'aula magna del dipartimento di Matematica dell'Università di Pisa e in diretta streaming su Google Meet https://meet.google.com/dwq-tvii-jga con i contributi di Matteo D'Achille (U. Parigi-Est), Luigi De Pascale (U. Firenze), Francesco Mattesini (U. Münster) ed Eugene Stepanov (U. San Pietroburgo). Maggiori informazioni sul programma, gli abstract dei talk e sulla registrazione all'evento (consigliata nel caso di partecipazione in presenza) sono disponibili alla pagina https://indico.cs.dm.unipi.it/event/12/overview Saluti, Dario Trevisan --- Dear all, I would like to announce the miniworkshop "Optimal Transport and Uncertainty" that will take place on Friday November 26, at Aula Magna, Department of Mathematics, University of Pisa. The event will be also live streamed on Google Meet https://meet.google.com/dwq-tvii-jga Main speakers are Matteo D'Achille (U. Paris Est), Luigi De Pascale (U. Firenze), Francesco Mattesini (U. Münster)and Eugene Stepanov (U. Saint Petersburg). For more information on the timetable and registration (strongly suggested in case you want to attend in presence) can be found at https://indico.cs.dm.unipi.it/event/12/overview Regards, Dario Trevisan -- Dario Trevisan, Università degli Studi di Pisa, Dipartimento di Matematica, Largo Bruno Pontecorvo 5, 56127 - Pisa (PI) Italy telephone: (+39) 050 2213832 mobile: (+39) 331 2899761 Skype: dario-trevisan e-mail: dario.trevisan AT unipi.it webpage: http://people.dm.unipi.it/trevisan/

1 0

Seminar by Sergio Pulido in Verona
by Alessandro Gnoatto 19 Nov '21

19 Nov '21

Sergio Pulido (École Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise) will give a talk at our Department. Date: 24 November 12:00 CET. Title: American options in the rough Heston model Abstract: Rough volatility models have emerged as compelling alternatives to classical semimartingale models to capture important stylized features of the implied volatility surface and the time series of realized volatility. The rough Heston model is particularly appealing because its affine structure facilitates the pricing of European options using Fourier techniques. In this work we consider the problem of pricing American options in the rough Heston model. The complexity of the problem stems from the absence of a Markovian-semimartingale structure in the model. To overcome this difficulty we work with a Markovian multi-factor semimartingale stochastic volatility model, which approximates the rough Heston model. In this approximated model, American options can be priced using a backward approach and simulation-based methods. We prove the convergence of American options prices in the multi-factor model towards the prices in the rough Heston model. The proof relies on the explicit expression of the conditional characteristic function of the joint forward process and the spot price, which is a consequence of the affine structure of the model. We illustrate with some numerical examples the behavior of American option prices with respect to some parameters in the model. This is joint work with Etienne Chevalier and Elizabeth Zuniga. If you would like to attend via Zoom, please register at the following link, we will send you the details: https://docs.google.com/forms/d/e/1FAIpQLSeVog1wfkFpBhehoYMRoTcNFESIOvh3Y-C… -- Alessandro Gnoatto Dipartimento di Scienze Economiche Università degli Studi di Verona Via Cantarane 24 37129, Verona, Italy Room 1.05 Tel: +39 045 802 8537 Homepage: www.alessandrognoatto.com E-mail: alessandro.gnoatto(a)univr.it -------------------------------------------------- View my research on my SSRN Author page: http://ssrn.com/author=1615989 --------------------------------------------------

1 0

Online Quantitative Finance Seminars @SNS, November 25, 2021 and December 10, 2021
by Giulia Livieri 19 Nov '21

19 Nov '21

Dear all, We would like to announce the following two Online Seminars @SNS: *November 25, 2021 at 4PM (CEST)* *Speaker: *Dr. Andrea Barbon (HSG) [webpage: http://www.abarbon.com/] *Title: *On The Quality Of Cryptocurrency Markets Centralized Versus Decentralized Exchanges (joint work with Prof. Angelo Ranaldo (HSG)). *Abstract: * Despite the growing adoption of decentralized exchanges, not much is yet known about their market quality. To shed some light on this issue, we study cryptocurrencies by comparing decentralized blockchain-based venues (DEX) to centralized crypto exchanges (CEX) by assessing two key aspects of market quality: price efficiency and market liquidity. Using a novel and comprehensive data set, we find that overall CEX provide better market quality but CEX becomes competitive if transaction costs exceed 100,000$. Further, the main determinant of the lower price-efficiency of DEX is the high gas price stemming from proof-of work blockchains. We propose and empirically validate a stylized theory of DEX liquidity provision, which links trading volumes, protocol fees, and liquidity in equilibrium. Our model prefigures the possible scenarios of efficiency paths for DEX to overtake CEX. *Link: * https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZDFlZmJkNDItYmVlNC00… ======================================================================== *December 10, 2021 at 3PM (CEST)* *Speaker: *Prof. Agostino Capponi (Columbia University) *Title: * The Adoption of Blockchain-based Decentralized Exchanges (joint work with Dr. Ruizhe Jia) *Abstract: *We show that the blockchain order execution mechanism and liquidity pooling create arbitrage rents in decentralized exchanges. The arbitrage rent raises the cost of liquidity provision and imposes negative externalities on users of the underlying blockchain. In equilibrium, automated market makers (AMMs) are adopted by liquidity providers only if exchange rates of token pairs are sufficiently stable. A pricing curve with higher curvature reduces arbitrage rents, but also decreases trading activities. We provide statistical support for our main model implications using transaction-level data of AMMs. *Link: * https://teams.microsoft.com/l/meetup-join/19%3ameeting_NjAyODk0YzQtNmVmYS00… We are looking forward to seeing you at the seminars! Best regards, Giulia

1 0

Workshop on Dynamic Optimization in Economics, Finance, and Insurance
by Marina DI GIACINTO 17 Nov '21

17 Nov '21

Dear Colleagues, We are pleased to announce the upcoming workshop "Dynamic Optimization in Economics, Finance, and Insurance", that will be hosted by Università Cattolica del Sacro Cuore - Milano in hybrid mode on November 26, 2021 at 10am. Details can be viewed in the attached advertisement. Best, Marina Di Giacinto

1 0

PhD in Statistics and Computer Science @Bocconi - call for applications
by Antonio Lijoi 17 Nov '21

17 Nov '21

******************* PhD in Statistics and Computer Science - a.y. 2022-2023 Call for applications for PhD student positions ******************* The Bocconi PhD School provides 7 scholarships for the PhD in Statistics and Computer Science, and a position with tuition waiver. * Scholarship amount * 20,000 euros per annum Further funding may be available through teaching and research assistantship. Visit www.unibocconi.eu/admissionphd for detailed information. ** Applications are due by February 1, 2022 ** Within the PhD School at Bocconi University, the four-year PhD program in Statistics and Computer Science is a high profile and rigorous doctoral program that develops strong mathematical, statistical, computational and programming backgrounds. The curriculum is structured into two tracks: Statistics and Computer Science. The first year includes courses that are compulsory for all enrolled PhD students. The second-year features track-specific and elective courses that provide students with a more specialized competence and focus on topics that may be the object of the doctoral dissertation. Dedicated mentorship is offered to students throughout their time at Bocconi. Multidisciplinary interchange with other graduate programs in Bocconi’s PhD School, as well as research experience abroad, are also encouraged. The Faculty includes internationally acknowledged top researchers in Statistics, Computer Science, Mathematical Analysis, Decision Theory, Statistical Physics and Machine Learning. The program also benefits from contributions of authoritative visiting professors who deliver short monographic courses. Highly qualified and motivated students with M.Sc. degrees in in Statistics, Mathematics, Computer Science, Economics, Physics, Engineering and related areas, as well as other quantitatively-oriented fields, are encouraged to apply for admission. Applicants should hold, or be on their way to hold, a graduate degree or equivalent. For further information about the PhD program in Statistics and Computer Science at Bocconi, visit www.unibocconi.eu/phdstatscompscience and feel free to contact: Antonio Lijoi (antonio.lijoi(a)unibocconi.it) Angela Baldassarre, PhD administrative assistant (angela.baldassarre(a)unibocconi.it)

1 0

Webinar Schlather @Bocconi
by Giacomo Zanella 17 Nov '21

17 Nov '21

We announce the following DEC Statistics webinar at Bocconi: Date: Thursday 18 November 2021, h12:00 (Italy time) Speaker: Martin Schlather (University of Mannheim) Title: A Generalized Approach to Principal Component Analysis Abstract: Principal Component Analysis is a well known procedure to reduce intrinsic complexity of a standardized data set, essentially through simplifying the correlation structure. We provide a substantial extension based on semi-groups, which includes distributions without second moments. We reformulate the PCA as a best low rank approximation defined through a regression problem, which is closely connected to autoencoders and admits solutions under mild assumptions. As a specific example, we apply our general formulation to extreme value distributions. In this case solving the regression problem reduces to a tractable and practically solvable problem for real datasets. As a side effect of our general approach, the perspective on uncorrelated variables is inverted: the assertion that the covariance is zero is not the definition, but a corollary; the fact that uncorrelated variables need not be independent is not a warning, but intrinsic to the definition. The webinar will be on zoom at: https://unibocconi-it.zoom.us/j/91941945297?pwd=VGhFVGc5OUVHUUFXQ2tlK0xQWkV… Meeting ID: 919 4194 5297 Passcode: 932042 Kind regards, Giacomo Zanella

1 0

[PHD Scholarship] "ADVANCED HEALTH ANALYTICS ON ADMINISTRATIVE DATA" @ Politecnico di Milano & Regione Lombardia - inizio febbraio 2022
by Laura Maria Sangalli 16 Nov '21

16 Nov '21

*** Con preghiera di diffusione URGENTE a tutti gli interessati *** Si segnala che, nell'ambito del Dottorato di Data Analytics and Decision Sciences (DADS<https://phd-dads.polimi.it/>) del Politecnico di Milano, è stata bandita una borsa dal tema "ADVANCED HEALTHCARE ANALYTICS ON ADMINISTRATIVE DATA" (dettagli e specifiche progettuali in calce). La borsa è parte di una dotazione più ampia di Borse di Dottorato, promosse da Regione Lombardia presso il Politecnico di Milano. Possono candidarsi laureati magistrali (o laureandi al più nella sessione di Dicembre 2021). Le selezioni si svolgeranno sulla base della valutazione dei titoli e del progetto di ricerca presentato. In caso di assegnazione della borsa, il dottorando dovrà obbligatoriamente svolgere un periodo di almeno 6 mesi di ricerca presso l'ente finanziatore (in questo caso Regione Lombardia - dg welfare), secondo le modalità definite dal bando. Link<http://www.dottorato.polimi.it/it/entra-al-dottorato/concorso-di-ammissione….> al bando. La scadenza per la presentazione della domanda è il 13 dicembre 2021, ore 14.00 (Italian time). Inizio: 1° febbraio 2022. Per informazioni, contattare francesca.ieva(a)polimi.it<mailto:francesca.ieva@polimi.it>. Cordialmente Francesca Ieva —— Laura Maria Sangalli MOX - Dipartimento di Matematica Politecnico di Milano Piazza Leonardo da Vinci 32 20133 Milano - Italy tel: +39 02 2399 4554 fax: +39 02 2399 4568 email: laura.sangalli(a)polimi.it<mailto:laura.sangalli@polimi.it> url: http://mox.polimi.it/~sangalli

1 0