- SIPTA News - lists.sipta.org

FW: dissertation of Dominik Hose
by Kreinovich, Vladik Nov. 21, 2022

Nov. 21, 2022

An interesting 2022 PhD dissertation by Dominik Hose "Possibilistic Reasoning with Imprecise Probabilities: Statistical Inference and Dynamic Filtering" is available at https://dominikhose.github.io/dissertation/diss_dhose.pdf

1 0

Two next SIPTA seminars: 29th November and 14th December (both 15:00 CEST))
by Sébastien Destercke Nov. 20, 2022

Nov. 20, 2022

Dear SIPTiAns and IP enthusiasts, We are delighted to announce our upcoming fifth and sixth SIPTA online seminars on imprecise probabilities (IP). These monthly events are open to anyone interested in IP, and will be followed by a Q&A and open discussion. They also provide an occasion for the community to meet, keep in touch and exchange between in-person events. The fifth seminar will take place on the 29th of November (Tuesday) and the sixth on the 14th of December (Wednesday), both at 3pm CEST. The zoom link for the next seminar (29th) is https://utc-fr.zoom.us/j/87301217403 For this fifth seminar, we are very happy to have Fabio Cozman as our speaker. Fabio Cozman is a Full Professor at Escola Politécnica (Poli), Universidade de São Paulo (USP), and Director of the Center for Artificial Intelligence at USP. He has made many core contribution to artificial intelligence in general, on such varied topics as graphical models, logic or machine learning. He is also interested in the very foundations of reasoning under uncertainty, and has made numerous core contributions to imprecise probability. On the 29th November, at 15:00 CEST (up to 17:00 CEST, with a talk duration of 45min/1h), he will talk about "Dealing with Uncertain Arguments in Artificial Intelligence”. Curious? Then check out the abstract on the webpage of the SIPTA seminars: sipta.org/events/sipta-seminars. The zoom link for attending the seminar can be found on that same page shortly before the event. So please mark your calendars on the 29th November, at 15:00 CEST, and join us for the occasion. And for those who missed the previous seminar and want to catch up, or simply want to see it again and again, it is now online at https://www.youtube.com/watch?v=g10_mhNfMWs. See you at the seminar! Sébastien, Enrique and Jasper

1 0

Springer special Issue in Annals of Mathematics and Artificial Intelligence: Recent advances in preference handling
by Sébastien Destercke Nov. 12, 2022

Nov. 12, 2022

Please forward this announcement to anyone who may be interested. Please accept our apology if you have received duplicate copies. ======================= Key information ====================== Special issue on recent advances in preference handling Description To submit: login to https://www.editorialmanager.com/amai/default2.aspx and when selecting article type, choose "S721: preference handling" (you may have to scroll down). Key dates: • Submissions deadline: 15th January 2023 • Feedbacks: two to three months after reception of the submission or its revision • Expected date of the special issue termination: 15th September 2023 Guest editors: Sébastien Destercke - corresponding editor (sebastien.destercke(a)hds.utc.fr) Meltem Ozturk Escoffi er (meltem.ozturk(a)dauphine.fr) Paolo Viappiani (paolo.viappiani(a)dauphine.psl.eu) Christophe Labreuche (christophe.labreuche(a)thalesgroup.com) Khaled Belahcene (khaled.belahcene(a)hds.utc.fr) =============================================================== Human-centered AI requires that AI systems are able to adapt to humans, to understand the preferences underlying human choice behavior, and to take them into account when interacting with humans or when acting on their behalf. Preference models are needed in decision-support systems such as web-based recommender systems, in digital assistants and chatbots, in automated problem solvers such as configurators, and in autonomous systems such as Mars rovers. Nearly all areas of artificial intelligence deal with choice situations and can thus benefit from computational methods for handling preferences while gaining new capabilities such as explainability and revisability of choices. Preference handling is also important for machine learning as preferences may guide learning behaviour and be subject of dedicated learning methods. Moreover, social choice methods are of key importance in computational domains such as multi-agent systems. Preferences are studied in many areas of artificial intelligence such as knowledge representation & reasoning, multi-agent systems, game theory, computational social choice, constraint satisfaction, logic programming and non-monotonic reasoning, decision making, decision-theoretic planning, and beyond. Preferences are inherently a multi-disciplinary topic, of interest to economists, computer scientists (including AI, databases, and human-computer interaction), operations researchers, mathematicians and more. Given the increasing importance of handling preferences and of AI methods in general, we are organizing a journal special issue focusing on the recent advances on preference handling and learning, be it through symbolic or numerical models. Topics covered in the special issue include • elicitation of preferences, • (statistical) learning of preferences, • uncertainty in preferences, • modelling and representation of preferences, • aggregation of preferences, • reasoning with preferences, • explaining preferences, • use of preferences in decision making (multicriteria, decision of group) database querying, web search, personalized human-computer interaction, personalized recommender systems, e-commerce, multi-agent systems, game theory, computational social choice, combinatorial optimization, automated problem solving, non-monotonic reasoning, planning and robotics, perception and natural language understanding, applications in particular domains (e.g., healthcare, sustainability). Deadlines and review process: Every submission will be thoroughly reviewed by at least two external reviewers and carefully supervised by one of the guest editors, who will make every effort to guarantee high quality standards. Submissions will be sent to reviewers as soon as they will be submitted, and quickly published on-line in case of acceptance. The guest editors Sébastien, Meltem, Paolo, Christophe and Khaled.

1 0

Fourth SIPTA seminar: 21th October, at 15:00 CEST, Ignacio Montes talking about "Coalitional game theory vs Imprecise probabilities: Two sides of the same coin ... or not?"
by Sébastien Destercke Oct. 12, 2022

Oct. 12, 2022

Dear SIPTiAns and IP enthusiasts, We are delighted to announce our third SIPTA online seminar on imprecise probabilities (IP). These monthly events are open to anyone interested in IP, and will be followed by a Q&A and open discussion. They also provide an occasion for the community to meet, keep in touch and exchange between in-person events. For this fourth seminar, we are very happy to have Ignacio Montes as our speaker. Ignacio Montes is currently Associate Professor at the Department of Statistics and Operations Research at the University of Oviedo, and has made many contributions to imprecise probabilities. He is well known for his contributions on rankings and on copulas within IP models, but has also made significant contributions to characterise practical models or to bridge notions between game theory and imprecise probabilities On the 21th October, at 15:00 CEST (up to 17:00 CEST, with a talk duration of 45min/1h), he will talk about "Coalitional game theory vs Imprecise probabilities: Two sides of the same coin ... or not?”. Curious? Then check out the abstract on the webpage of the SIPTA seminars: sipta.org/events/sipta-seminars. The zoom link for attending the seminar will appear on that same page shortly before the event. So please mark your calendars on the 21th October, at 15:00 CEST, and join us for the occasion. And for those who missed the previous seminar and want to catch up, or simply want to see it again and again, it is now online at https://www.youtube.com/watch?v=PFLBWTeW0II. See you at the seminar! Sébastien, Enrique and Jasper

1 0

FW: New book dealing with stochastic, fuzzy sets-based, and convex models of uncertainty
by Kreinovich, Vladik Oct. 2, 2022

Oct. 2, 2022

1 0

Call for papers: Thirteenth International Symposium on Imprecise Probabilities: Theories and Applications- Oviedo, 11-14 July, 2023
by Enrique Miranda Sept. 30, 2022

Sept. 30, 2022

The Thirteenth International Symposium on Imprecise Probabilities: Theories and Applications (ISIPTA 2023) What if we told you that “There’s more to uncertainty than probabilities.” Curious? Then come to Oviedo, Spain, 11-14 July 2023, to attend the 13th edition of ISIPTA: the world’s main forum on imprecise probabilities. For more information, visit https://isipta23.sipta.org/. Not convinced yet? Then perhaps the following features can convince you: TOPIC: The symposium is open to contributions on all aspects of imprecise probabilities, including (but not limited to) sets of probability measures, partial preference orderings, game-theoretic probability, choice functions, interval probabilities, belief functions, Choquet capacities, comparative orderings, upper and lower expectations and possibility theory. CONCEPT: Each accepted contribution is presented and discussed in two separate sessions. Presentations are short and plenary. Detailed explanations and discussions are face-to-face relying on whichever medium you prefer, so as to favor interaction among participants (you can visit the SIPTA website for links to the previous editions of all ISIPTA conferences). WHY ATTEND? The conference is an excellent opportunity to learn about the latest developments in imprecise probability in a friendly and cooperative atmosphere where interaction and confrontation of ideas are the primary objectives. The conference will take place in Oviedo, the capital of Asturias, a region in the north of Spain familiarly referred to as the Natural Paradise. In addition, Oviedo is the original starting point of the primary cultural route in Europe, the Way of St James, and is home to five pre-Romanesque monuments declared World Heritage Sites by UNESCO in 1985 and 1998. SUBMISSIONS: 2 options are available -Papers (with a limit of 9 pages, excluding references); -Abstracts (1 page, for ongoing research) Submission should be done via easychair: https://easychair.org/conferences/?conf=isipta2023. IMPORTANT DATES: -Submission of title +abstract: January 29, 2023. -Paper submission deadline: February 5, 2023 -Notification of paper acceptance: April 5, 2023 -Poster submission deadline: May 1, 2023 -Notification of poster acceptance: May 15, 2023 -Conference: 11-14 July 2023 TRIBUTE TO TERRENCE FINE: During ISIPTA 2023, we will pay tribute to Terrence Fine, one of the founding fathers of imprecise probability theory, who sadly passed away on January 31, 2021. More information shall be provided in due time. PROCEEDINGS: Papers will be published by PMLR (Proceedings of Machine Learning Research). After the conference, extended versions of selected conference contributions will be published in a special issue of the International Journal of Approximate Reasoning. FELLOWSHIPS: The Artificial Intelligence Journal is funding 4 fellowships for PhD Students. More information on the conditions and applications will be given in due time. AWARDS: As in previous editions, there will be two types of awards: On the one hand, the International Journal of Approximate Reasoning will give the IJAR Young Researcher Award to a young researcher whose contributions to IP theory are outstanding. The award shall consist of a certificate and 1000 euros. More details shall be given soon. In addition, poster awards shall be given to those poster presentations of excellent quality. The award shall be supported by Wiley and Springer and will consist of a certificate and a book. Contact e-mail: isipta2023(a)uniovi.es Further information: https://isipta23.sipta.org/ Twitter account: @isipta2023 The ISIPTA 2023 Steering Committee J. De Bock (Ghent University, Belgium) F.G. Cozman (University of Sao Paulo, Brazil) E. Miranda (University of Oviedo, Spain) I. Montes (University of Oviedo, Spain) E. Quaeghebeur (Eindhoven University of Technology, The Netherlands) B. Vantaggi (Università La Sapienza of Rome, Italy)

1 0

New SIPTA blog post
by Henna Bains Sept. 22, 2022

Sept. 22, 2022

Dear SIPTA community, After three years of research and extensive brainstorming, Tathagata Basu defended his thesis entitled “High dimensional statistical modelling under limited information” on the 15th December 2020. Would you like to find out more about Tatha’s research? Head over to the latest SIPTA blog post <https://sipta.org/blog/thesis-tathagata/>, where Tatha gives an overview of his thesis. Are you interested in writing a post for the SIPTA blog? Get in touch with Henna and Diego at blog(a)sipta.org. Kind regards, Henna and Diego (SIPTA blog editors)

1 0

ERRATUM Third SIPTA seminar: 29th September, NOT 27th september
by Sébastien Destercke Sept. 22, 2022

Sept. 22, 2022

Dear SIPTiAns and IP enthusiasts, In my rush to announce the seminar and due to my impatience to hear it, I made a small mistake: it is on the 29th on Thursday, not the 27th. Best regards Sébastien

1 0

Third SIPTA seminar: 27th September, at 15:00 CEST, Peter Grunwald talking about "E is the new P"
by Sébastien Destercke Sept. 21, 2022

Sept. 21, 2022

Dear SIPTiAns and IP enthusiasts, We are delighted to announce our third SIPTA online seminar on imprecise probabilities (IP). These monthly events are open to anyone interested in IP, and will be followed by a Q&A and open discussion. They also provide an occasion for the community to meet, keep in touch and exchange between in-person events. For this third seminar, we are very happy to have Peter Grunwald as our speaker. Peter Grunwald currently heads the machine learning group <http://safestatistics.com/group/> at CWI <http://www.cwi.nl> in Amsterdam, and has made many core contribution to statistics and machine learning over the years, including a book on Minimum Description Length Principle, as well as contributions to imprecise probabilistic reasoning as well as safe statistical inferences. On the 27th September, at 15:00 CEST (up to 17:00 CEST, with a talk duration of 45min/1h), he will talk about "E is the new P”. Curious? Then check out the abstract on the webpage of the SIPTA seminars: sipta .org/events/sipta-seminars. The zoom link for attending the seminar will appear on that same page shortly before the event. So please mark your calendars on the 27th September, at 15:00 CEST, and join us for the occasion. And for those who missed the previous seminar and want to catch up, or simply want to see it again and again, it is now online at https://www.youtube.com/channel/UCPER8Dfil66KZCYlsK86XCQ/featured. See you at the seminar! Sébastien, Enrique and Jasper

1 0

DA2PL 2023: final call for papers (deadline: 15 september)
by Sébastien Destercke Sept. 9, 2022

Sept. 9, 2022

===========FINAL CALL FOR PAPERS============ DA2PL 2022: From Multiple Criteria Decision Aid to Preference Learning Université de Technologie de Compiègne, France November 17-18, 2022 https://da2pl.pre.utc.fr/ ======== AIM ======== DA2PL 2022 (From Multiple Criteria Decision Aid to Preference Learning) aims to bring together researchers from decision analysis and machine learning. It provides a forum for discussing recent advances and identifying new research challenges in the intersection of both fields, thereby supporting a cross-fertilisation of these disciplines. Following the five previous editions of this workshop, which took place in Mons in 2012, Paris in 2014, Paderborn in 2016, Poznan in 2018, and Trento (virtually) in 2020, DA2PL 2022 will be held at the Université de Technologie de Compiègne (nearby Paris), France, the 17 and 18 november. =================== Keynote SPEAKERS =================== We are delighted to announce that the following persons have accepted to give a keynote speech at the conference: * Denis Bouyssou, Université Paris Dauphine, LAMSADE * Nicolas Usunier, Meta AI research * Thomas Augustin, Ludwig Maximilian University of Munich =================== AMAI special issue =================== We are also happy to announce that, in partnership with the journal "Annals of Mathematics and Artificial Intelligence", we will propose to authors of selected papers to submit an extended version of their submission to an AMAI special issue focusing on recent advances of preference handling. ================= Important dates ================= May 1st: submissions open September 15th: paper submission deadline (extended and final) October 10th: author notification November 3rd: Camera-ready version of papers November 17-18: Conference ======================== DA2PL 2022 vs COVID-19 ======================== We expect DA2PL to be mainly a physical event. We will provide a virtual option for participants wishing to be there remotely, but will request at least one full registration per submitted paper. ======== TOPICS ======== DA2PL 2022 solicits contributions to the usage of theoretically supported preference models and formalisms in preference learning as well as communications devoted to innovative preference learning methods in decision analysis and multicriteria decision aiding. Specific topics of interest include, but are not limited to: - quantitative and qualitative approaches to modelling preferences, user feedback and training data; - preference representation in terms of graphical models, logicalformalisms, and soft constraints; - dealing with incomplete and uncertain preferences; - preference aggregation and disaggregation; - learning utility functions using regression-based approaches; - preference elicitation and active learning; - preference learning in combinatorial domains; - learning relational preference models and related regression problems; - classification problems, such as ordinal and hierarchical classification; - inducing monotonic decision models for preference representation; - comparison of different preference learning paradigms (e.g., monolithic vs. decomposition); - ranking problems, such as object ranking, instance ranking and label ranking; - complementarity of preference models and hybrid methods; - explanation of recommendations; - applications of preference learning, such as web search, information retrieval, electronic commerce, games, personalization, recommender systems, … ============= Submissions ============= Submissions must be written in English and formatted according to the electronic template that is available at https://da2pl.pre.utc.fr/wp-content/uploads/sites/70/2022/03/DA2PL22_templa… The page limit is 8 for full papers, although extended abstracts (maximum two pages) are welcome, too. As usual for DA2PL, submissions are NOT anonymous. According to the template, names of authors should be stated in the manuscript. All submissions will be reviewed by at least two referees. Submissions must be submitted through EasyChair at https://easychair.org/conferences/?conf=da2pl Following a successful experience from the latest editions, DA2PL will provide a special opportunity for doctoral students to explore and develop their research interests. A special session at the conference will be devoted to PhD students, for presenting and discussing their ongoing research work. Therefore, we specifically encourage young researchers to submit their work (as full paper or extended abstract, depending on the maturity of the PhD project); the submission site will provide the option to mark a submission as a student paper. =========================== Organization and contacts =========================== General chairs Khaled Belahcene, Université de Technologie de Compiègne (khaled.belahcene(a)hds.utc.fr) Sébastien Destercke, Université de Technologie de Compiègne (sebastien.destercke(a)utc.fr)

1 0