- Random - Mailing list — Dipartimento di Matematica, UniPI

[SURE-AI@STAR Midsummer on Reinforcement Learning] June 23-25 - Xin Guo
by Leonardo Tarquini 02 Jun '26

02 Jun '26

Dear all, Join us for our upcoming workshop SURE-AI@STAR Midsummer on Reinforcement Learning. The event will take place on three different days in a hybrid format: participants in Oslo can attend the talk in Room 723 in Niels Henrik Abels hus, whereas the international audience will be able to follow the talk via Zoom (see link next to each talk). The lecturer is Xin Guo (UC Berkeley). Title: A control-theoretical perspective of continuous-time reinforcement learning Abstract: Reinforcement Learning (RL) is a cornerstone of modern machine learning, enabling agents to learn optimal decision-making through interaction with complex environments and other agents. While RL was traditionally developed for discrete-time settings, many real-world physical and financial systems are intrinsically continuous. This series of lectures provides a comprehensive overview of recent advancements in continuous-time RL, analyzed through the rigorous lens of stochastic control theory. It consists of three parts. Registration<https://nettskjema.no/a/630234> is free, but mandatory for both in-person and online attendees to ensure the best logistics. The seminar link will be shared with all registered participants before the event starts. Part I. Foundations: Q-Functions and Dynamic Programming (23/06/2026, 13:00-16:00) We begin by establishing a bridge between RL and classical control theory. By leveraging the Dynamic Programming Principle (DPP) and the Feyman-Kac formula, we explore the similarities between these fields, specifically through the lens of continuous-time Q-functions, and martingale characterization. References [1] Gu, Guo, Wei, Xu (2020). Dynamic programming principle for mean field controls with learning. Operations Research, 2023. Arxiv: 1911.07314. [2] Gu, X. Guo, Wei, Xu (2021) Mean-Field controls with Q-learning for cooperative MARL: convergence and complexity analysis. SIAM Journal on Mathematics of Data Science. ArXiv:2002.04131. [3] Cheng, Guo, Zhang (2025). Bridging discrete and continuous RL: stable deterministic policy gradient with martingale characterization. arXiv:2509.23711. Part II. The Theoretical Divide: Regret Analysis and BSDEs (24/06/2026, 13:00-16:00) To distinguish RL from classical control, we analyze ``the cost of learning'' through regret analysis. This section delves into the mathematical tools required to quantify performance gaps when the system model is unknown. We show how the regularity of Hamilton-Jacobi-Bellman (HJB) equations and Backward Stochastic Differential Equations (BSDEs) enables establishing regret bounds. In the particular case of Linear-Quadratic (LQ) Models: we present proofs for logarithmic regret in episodic finite-horizon RL via regularities of the Riccati equation. References [4] Basei, Guo, Hu, Zhang (2020). Logarithmic regret for episodic continuous-time linear-quadratic reinforcement learning over a finite-time horizon. Journal of Machine Learning Research. Arxiv.org/abs/2006.15316<http://arxiv.org/abs/2006.15316>. [5] Guo, Hu, Zhang (2021). Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls. SIAM J. on Control Optimization (SICON). Arxiv.org/abs/2104.09311<http://arxiv.org/abs/2104.09311>. Part III. Modern Frontiers: Transfer Learning and Rough Paths (25/06/2026, 13:00-16:00) Finally, we explore how cutting-edge developments from Large Language Models (LLMs), such as transfer learning, can be integrated into RL to significantly boost algorithmic performance. We discuss fast policy learning for LQ control using entropy techniques to balance exploration and exploitation. We will also uncover how the regularity of rough paths provides a framework for analyzing policy transfer in continuous-time RL, offering a robust mathematical foundation for cross-domain adaptation. References [6] Guo, Li, Xu (2025). Fast policy learning for linear quadratic control with entropy regularization. SICON. ArXiv:2311.14168. [7] Cao, Gu., Guo, and Rosenbaum (2024). Transfer learning for portfolio optimization. arXiv:2307.13546. [8] Guo. and Lyu (2025). Policy transfer for continuous-time reinforcement learning: a (rough) differential equation approach, arxiv2510.15165. The seminar is in the interest of SURE-AI - Sustainable, Risk-Averse and Ethical AI<https://www.sure-ai.no/>. We are looking forward to seeing you! Best regards, Giulia, Leonardo, Pere, and David

1 0

PhD position at WIAS Berlin - deadline 18 June
by Alexander Zass 02 Jun '26

02 Jun '26

Buongiorno, ricevo e con piacere inoltro l’annuncio di una posizione di dottorato al Weierstrass Institute di Berlino. Cordialmente, Alexander Zass ----- Von: Willem van Zuijlen <vanzuijlen(a)wias-berlin.de <mailto:vanzuijlen@wias-berlin.de>> ----- Dear all, I am looking for a motivated candidate with a background in mathematical probability and/or analysis for a PhD student position at WIAS Berlin. The key task is to study the behaviour of stochastic processes in random environments, for example those that describe the evolution of stochastic partial differential equations. The application deadline is June 18, 2026. For more information, see https://wias-berlin.softgarden.io/job/64846351?l=de Best wishes, Willem van Zuijlen

1 0

Expression of Interest for Future Recruitment at the Department of Mathematics of the University of Turin
by Federico Polito 01 Jun '26

01 Jun '26

Dear colleagues, We are pleased to share that our Department has opened a call for expressions of interest for an Associate Professor position in Probability, which is included below. Interested junior researchers in Probability, for whom a tenure-track position (RTT) may be more appropriate, are also invited to express their interest via this separate form. <https://docs.google.com/forms/d/e/1FAIpQLScBtSQm1buMOvNqZviCapRL_qAhDwaONxS…> Please feel free to contact me for further information. Best regards, Federico Polito *%%%%%%%%%%%%%%%%%%%%%%%%* *Expression of Interest for Future Recruitment at the Department of Mathematics of the University of Turin* The Department of Mathematics “G. Peano” of the University of Turin invites expressions of interest from scholars who may be interested in future recruitment opportunities at the rank of *Associate Professor * over the next three years. The Department is particularly interested in candidates currently working in Italy or abroad in the areas of *Probability* or *Numerical Analysis*. However, applications from outstanding candidates in all fields of Mathematics will be carefully considered. Expressions of interest regarding other type of positions are also welcome. The call for applications will remain open for the next three years, and a first deadline is *30 June 2026*. As to associate positions, eligible candidates should not have held academic positions at the University of Turin during the last three years. Interested scholars are invited to send: - a brief expression of interest, - a current curriculum vitae, and - a research statement to the Director of the Department of Mathematics at the following email address: direzione.matematica(a)unito.it stating the words ‘expression of interest’ and their name in the subject line. These expressions of interest are intended solely to help the Department identify potential candidates for future recruitment opportunities and do not constitute a commitment to recruit. Positions will be opened in accordance with the strategic recruiting plan of the University of Turin. We encourage interested colleagues to contact us and to circulate this notice within the mathematical community. ================================== °°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°°° Susanna Terracini Direttrice Dipartimento di Matematica "Giuseppe Peano" Università di Torino https://sites.google.com/site/susannaterracini/ susanna.terracini(a)unito.it susanna.terracini(a)gmail.com -- Federico Polito Professor of Probability Coordinator of M.Sc. in Stochastics and Data Science *Department of MathematicsUniversity of Torino* Via Carlo Alberto, 10 10123, Torino, Italy Email: federico.polito(a)unito.it Tel: +39 011 6702919 Web: 0fpl.github.io

1 0

6+2 PhD positions at Tor Vergata (one in probability/math physics)
by Michele Salvi 29 May '26

29 May '26

Dear all, I am pleased to inform you that the call for applications for the 42nd cycle of the PhD Program in Mathematics at the University of Rome Tor Vergata, for the academic year 2026/2027, has been published. The deadline for applications is June 09, 2026, at 12:00 PM (Italian time). We are advertising 8 PhD positions in Mathematics, distributed as follows: -- 6 full scholarships in all areas of mathematics; -- 1 full scholarship in Probability/Mathematical Physics, supervised by Giorgio Cipolloni (https://giorgiocipolloni.github.io <https://giorgiocipolloni.github.io/>); -- 1 full scholarship in Geometry, supervised by Eleonora Di Nezza (https://perso.pages.math.cnrs.fr/users/eleonora.di-nezza/) Please do not hesitate to contact Giorgio or Eleonora if you are interested in one of these two specific positions. For more information: https://dottorati.uniroma2.it/42-ciclo_p10363.aspx (PhD call) https://phd.uniroma2.it/web/concorso42.aspx?s=&i=1012&m=&l=&p=&a= (Description of Math PhDs) Best, Michele

1 0

Contratti di ricerca e incarico post doc Dipartimento di Scienze Statistiche Università di Padova
by Livia Mian 29 May '26

29 May '26

Gentilissime/i, segnaliamo l’apertura delle seguenti posizioni presso il Dipartimento di Scienze Statistiche dell’Università di Padova: - *Contratto di ricerca durata 24 mesi,* referente: Prof.ssa Maria Sironi, finanziato dal Progetto: Living Alone, Loneliness, and Social Isolation Over Time and Across Space (SOLO), Bando FIS 3 SH7 Advanced Grant. Link al bando: https://www.stat.unipd.it/news/termine/99 <https://www.stat.unipd.it/news/termine/99> - *Contratto di ricerca durata 24 mesi*, referente: Prof. Marco Tosi, finanziato dal Progetto: Kin matter: Exploring the impact of kinship networks on health and social inequalities (Kin matter), Bando FIS 3 SH7 Consolidator Grant. Link al bando: https://www.stat.unipd.it/news/termine/99 - *Incarico postdoc durata 12 mesi,* referente: Dott.ssa Margherita Silan, finanziato dal progetto: Data Integration Approaches for a Multidimensional hOlistic representation Neighbourhood Deprivation (DIAMOND), Bando FIS 3 SH7 Starting Grant. Link al bando: https://www.stat.unipd.it/news/termine/102 La scadenza per tutte tre le posizioni è fissata all’8 giugno 2026, ore 13:00 Cordiali saluti, Il Dipartimento di Scienze Statistiche *** Dear all, We inform you that the following positions are open at the Department of Statistical Sciences of the University of Padova: - *Research contract for 24 months,* scientific responsible: Prof.ssa Maria Sironi, funded by the Project “Living Alone, Loneliness, and Social Isolation Over Time and Across Space (SOLO)”. Bando FIS 3 SH7 Advanced Grant. Link: https://www.stat.unipd.it/news/termine/99 - *Research contract for 24 months,* scientific responsible: Prof. Marco Tosi, funded by the project Kin matter: Exploring the impact of kinship networks on health and social inequalities (Kin matter), Bando FIS 3 SH7 Consolidator Grant. Link: https://www.stat.unipd.it/news/termine/99 - *Post doc position for 12 months*, scientific responsible: Dott.ssa Margherita Silan, funded by the project Data Integration Approaches for a Multidimensional hOlistic representation Neighbourhood Deprivation (DIAMOND), Bando FIS 3 SH7 Starting Grant. Link: https://www.stat.unipd.it/news/termine/102 The deadline for the three positions is scheduled for 8 June 2026, 1:00 pm. Best regards, The Department of Statistical Sciences

1 0

Seminars in Statistics at Collegio Carlo Alberto - Sara WADE (UNIVERSITY OF EDINBURGH)
by Matteo Giordano 29 May '26

29 May '26

SEMINARS IN STATISTICS @ COLLEGIO CARLO ALBERTO <https://www.google.com/url?q=https://www.carloalberto.org/events/category/s…> Venerdì 05/06/2026, presso il Collegio Carlo Alberto, in Piazza Arbarello 8, Torino, si terrà il seguente seminario: ------------------------------------------------ 12.00-13.00 Speaker: Sara WADE (UNIVERSITY OF EDINBURGH) Title: Explainable Bayesian learning Abstract: The Bayesian approach is widely valued for its principled treatment of uncertainty and its ability to propagate this uncertainty to predictions. However, advances in modeling and data acquisition have led to posterior distributions defined over increasingly complicated parameter spaces, making them difficult to interpret and summarize. This challenge extends to predictive distributions, which in modern applications may reside on non‑standard spaces such as partitions, sequences, or graphs. In this work, we develop tools for explaining and summarizing non‑standard posterior and predictive distributions arising in Bayesian learning. We illustrate the core ideas in context of clustering, utilizing the Wasserstein distance to obtain a succint, discrete summary of posterior distributions on the space of partitions. We further outline extensions to clustering with clutter and variable selection, and demonstrate how the proposed tools remain useful beyond the Bayesian setting when data itself is uncertain. ------------------------------------------------ Sarà possibile seguire il seminario anche in streaming: chiunque volesse collegarsi è pregato di inviare un’email a matteo.giordano(a)unito.it <mailto:matteo.giordano@unito.it> Il webinar è organizzato dalla "de Castro" Statistics Initiative (www.carloalberto.org/stats <http://www.carloalberto.org/stats>) in collaborazione con il Collegio Carlo Alberto. Cordiali saluti, Matteo Giordano Assistant Professor (RTDA) Department of Economics, Social Studies, Applied Mathematics and Statistics (ESOMAS) www.matteogiordano.weebly.com <https://matteogiordano.weebly.com/>

1 0

PhD call in Mathematics UniTn-UniVr
by Luca Di Persio 29 May '26

29 May '26

Dear all, I am writing to inform you about the publication of the call for applications for the PhD Program in Mathematics, 42nd cycle (academic year 2026/2027), jointly steered by the University of Trento and the University of Verona, expiring on June 20, 2026, at 4:00 PM (Italian time). For more information: * PhD Course Mathematics<https://www.unitn.it/en/phd/mathematics> [general information on the School and how to apply] * PhD Organization and Impact<https://phd.unitn.it/drmath/4/doctoral-programme-mathematics-agreement-univ…> [with a dedicated section on Regulations and School Organization]. An online Open Day meeting<https://sites.google.com/unitn.it/opendayphdmath/#h.u71vp6xgkckf> among professors, researchers, PhD students, and potential candidates, is also planned for June 10, 2026, starting at 2 pm (Italian time). Students potentially interested in research topics that are related to stochastic analysis and its applications are more than welcome. Do not hesitate to contact me at luca.dipersio(a)univr.it<mailto:luca.dipersio@univr.it> for any further informations Best, LuCa __ Luca Di Persio - PhD College of Mathematics Dept. of Computer Science University of Verona strada le Grazie 15 - 37134 Verona - Italy Tel : +39 045 802 7968

1 0

Post-doc announcement
by Mario Maurelli 28 May '26

28 May '26

Dear colleagues, Below you find the following announcement from Julian Tugaut, for a post-doc under his supervision, on the framework of Marie Curie program: https://euraxess.ec.europa.eu/jobs/435626 Deadline June 1st. For any enquiries you can contact: Julian Tugaut Professeur des Universités Institut Camille Jordan (UMR 5208) Les Forges II, 20 rue du Dr Annino 42000 SAINT-ÉTIENNE CEDEX 2 FRANCE (0033)(0) 469 663 204 julian.tugaut(a)univ-st-etienne.fr http://tugaut.perso.math.cnrs.fr https://www.univ-st-etienne.fr/fr/icj.html Best regards Mario Maurelli

1 0

Seminario Syed Ejaz Ahmed | "Bridging Weak Signals and Sparsity: A Post-Shrinkage Perspective" (08.06.2026)
by Eventi Stat 28 May '26

28 May '26

Buongiorno, *lunedì 8 giugno alle 10.30* il Prof. *Syed Ejaz Ahmed* (Brock University) terrà il seminario di ricerca "*Bridging Weak Signals and Sparsity: A Post-Shrinkage Perspective*". Il seminario si svolgerà in presenza nell'Aula Benvenuti del Dipartimento di Scienze Statistiche, Università di Padova. Tutti gli interessati sono invitati a partecipare. ******** *Thursday 8 Jun at 10.30 a.m.*, *Syed Ejaz Ahmed* (Brock University) will hold a seminar entitled "*Bridging Weak Signals and Sparsity: A Post-Shrinkage Perspective*". The seminar will be held in the Benvenuti room of the Department of Statistical Sciences, University of Padova. L'elenco dei seminari in programma è disponibile qui: www.stat.unipd.it/ricerca/academic-year-20252026. Per ulteriori informazioni, si prega di contattare il referente dei seminari del Dipartimento (Emanuele Aliverti, emanuele.aliverti(a)unipd.it)

1 0

Reminder: OWABI - Kate Lee - May 28, 10am UK time
by Massimiliano Tamborrino 26 May '26

26 May '26

Dear all, a kind reminder that the next OWABI seminar www.warwick.ac.uk/owabi<http://www.warwick.ac.uk/owabi> of the Season is on Thursday the 28th May at 10am UK time (a wrong date was circulated before, apologies for that!), when Kate Lee<https://profiles.auckland.ac.nz/kate-lee> <https://profiles.auckland.ac.nz/kate-lee> (University of Auckland) will talk about "Towards Robust and Scalable Bayesian Learning". The talk will be streamed on the OWABI MS Teams Channel General | OWABI Seminar: One World Approximate Bayesian Inference Seminar<https://teams.microsoft.com/l/team/19%3AdhZ_4e_XLNJzCXPAMzTvT6BZ5KShEETkd_w…> at this link https://teams.microsoft.com/meet/382746871856192?p=U7SJQ144q6hLNVFGdS Meeting ID: 382 746 871 856 192 Passcode: FZ2gn73K Speaker: Kate Lee<https://profiles.auckland.ac.nz/kate-lee> (University of Auckland) Title: Towards Robust and Scalable Bayesian Learning Abstract: My talk consists of two parts. The first focuses on Generalised Bayesian Inference (GBI), where the loss hyperparameters are critical under model misspecification yet difficult to determine in a principled way. We introduce a Bayesian framework for hyperparameter inference using held-out data, enabling coherent estimation and uncertainty quantification, together with amortized generalized-posterior approximations that avoid repeated costly sampling across datasets and hyperparameter values. The second addresses scalability in simulation-based inference through data reduction, developing methods that learn informative low-dimensional summaries to enable efficient inference in complex settings, with applications to gravitational wave analysis. Keywords: GBI, SBI, amortized learning We're looking forward to seeing you next week, best, Massimiliano on the behalf of the OWABI Seminar Organisers ------ Dr. Massimiliano Tamborrino SFHEA Reader (Associate Professor) Department of Statistics WIHEA Fellow and Internationalisation Learning Circle Co-Lead University of Warwick https://warwick.ac.uk/tamborrino

1 0