- SIPTA News - lists.sipta.org

Reminder: Kevin Blackwell talk at 3pm
by sdesterc Nov. 26, 2025

Nov. 26, 2025

Dear Siptians, This is just a reminder that Kevin Blackwell talk will take place at 3pm. Information (including zoom link) there: https://sipta.org/events/sipta-seminars/ See you in an hour! Sébastien

1 0

Re: SMPS 2026 in Lecce, Italy, September 15-18, 2026
by Kreinovich, Vladik Nov. 24, 2025

Nov. 24, 2025

Dear Colleagues, the SMPS 2026 conference (Soft Methods in Probability and Statistics) will take place on September 15-18, 2026, in Lecce, Italy. As is customary for the SMPS series, we expect between 80 and 120 participants, creating an environment conducive to stimulating scientific dialogue and a warm, friendly atmosphere. Our objective is to keep the fees including lunches, conference dinner, social events and Springer book of proceedings as low as possible. In the conference website, you may find the expected fees (the precise amounts will be determined in the spring, once the exact number of participants is known). Confirmed plenary speakers are: • Bernard De Baets (Ghent University, BE) • Irene Gijbels (KU Leuven, BE) • Beatriz Sinova Fernández (Oviedo University, ES) The SMPS conference series has the tradition to collect short papers of 6-8 pages of all participants giving a talk. These papers will undergo a quick peer-review and should either contain novel results or provide a survey over recently established material. All accepted contributions will be published in a forthcoming Springer conference proceedings book. Submission of short papers will be possible starting January 1st, 2026. For more information about the event, please check in the following days the official conference website: http://smps2026.unisalento.it<http://smps2026.unisalento.it/> the Linkedin page: https://www.linkedin.com/in/smps-lecce-7419b0398 Looking forward to welcoming you in Lecce Fabrizio Durante (for the Local Organizing Committee) --------------------------------------------------------- Fabrizio Durante Dipartimento di Matematica e Fisica “Ennio De Giorgi” Università del Salento via per Arnesano, I-73100 Lecce (Italy) Personal website: https://sites.google.com/site/fbdurante/ [Image removed by sender.]

1 0

Fwd: WUML 2026 – Workshop on Uncertainty in Machine Learning, Tartu, Estonia, Feb 2–4, 2026
by sdesterc Nov. 21, 2025

Nov. 21, 2025

Dear all, The next WUML conference on uncertainty in machine learning will take in Tartu during February. This is a nice workshop that promotes discussion around Machine learning. People attending usually have a very nice experience and in many occasion follow-up collaborations. Best regards Sébastien -- ==================================== Sebastien Destercke, Ph. D. CNRS researcher in computer science. Université de Technologie de Compiegne U.M.R. C.N.R.S. 7253 Heudiasyc Avenue de Landshut F-60205 Compiegne Cedex FRANCE Tel: +33 (0)3 44 23 79 85 Fax: +33 (0)3 44 23 44 77 ==================================== > Begin forwarded message: > > From: Meelis Kull <meelis.kull(a)ut.ee> > Subject: WUML 2026 – Workshop on Uncertainty in Machine Learning, Tartu, Estonia, Feb 2–4, 2026 > Date: 3 November 2025 at 11:15:32 CET > To: Meelis Kull <meelis.kull(a)ut.ee> > > Dear colleague, > > We are pleased to announce that the Workshop on Uncertainty in Machine Learning (WUML 2026) will be held on February 2–4, 2026, at the University of Tartu, Estonia. > > Following the successful previous editions in Munich (2024) and Milan (2025), WUML 2026 will continue to provide an open and informal forum for discussing recent advances and challenges in uncertainty in machine learning. > > The first WUML workshop was held in 2015, and the event has been held annually since 2023, with recent editions in Ghent, Munich, and Milan. The goal of this workshop is to bring together researchers interested in the topic of uncertainty in machine learning. It aims to provide a forum for discussing the latest developments in modeling and quantifying uncertainty in machine learning problems, as well as for exploring new research directions in this field. > > As in previous years, WUML 2026 will be an informal event without a paper submission system. Participants are welcome to give a talk, present a poster, or simply attend the workshop. Participation is free of charge, though attendees are expected to cover their own travel and accommodation expenses. > > Preliminary information about the workshop is available at: > https://sites.google.com/view/wuml2026 > > Those interested in attending are kindly asked to confirm their participation by January 7, 2026, using the following form: > https://forms.gle/Gom361htiTd48pfU9 > > Please note that, due to room capacity and expected interest, participation will be limited to a maximum of 150 attendees. > > For any questions, please feel free to contact the organizers. You are also welcome to share this announcement with colleagues or students who may be interested in attending. > > We look forward to seeing you in Tartu! > > On behalf of the WUML 2026 Organizing Committee > Meelis Kull > > > > --- > Meelis Kull > Head of the Estonian Centre of Excellence in AI > Professor of Artificial Intelligence > Institute of Computer Science > University of Tartu > meelis.kull(a)ut.ee <mailto:meelis.kull@ut.ee> >

1 0

Next SIPTA virtual seminar: 26th of November, K. Blackwell "Representing awareness change with sets of desirable gambles"
by sdesterc Nov. 18, 2025

Nov. 18, 2025

Dear colleagues, We are delighted to announce our upcoming 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. The next seminar will take place on the 26th of November (Wednesday). The zoom link for this seminar is https://utc-fr.zoom.us/j/83908951605 For this new seminar, we are very happy to have Kevin Blackwell as our speaker. Kevin Blackwell is currently a lecturer at Bristol Philosophy department, and has many contribution in the foundation of imprecise probabilities, with a recent focus on its most general forms using the notions of desirable gambles and of coherent choice functions. On the the 26th of November, at 15:00 CEST:paris time (up to 17:00 CEST, with a talk duration of 45min/1h), he will talk about "Representing awareness change with sets of desirable gambles”. 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. So please mark your calendars on the 26th of November, 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 online at https://www.youtube.com/watch?v=Fk1YvCstMRw See you at the seminar! Sébastien, Enrique and Jasper

1 0

FYI: interval session at NAFIPS 2026 conference, deadline for submissions December 1, 2026
by Kreinovich, Vladik Nov. 15, 2025

Nov. 15, 2025

Papers related to interval-valued and fuzzy-valued probabilities are always welcome at this series of fuzzy conferences *********** Special Session on Interval Uncertainty Organizers: Martine Ceberio (University of Texas at El Paso), Christoph Lauter (University of Texas at El Paso), Vladik Kreinovich (University of Texas at El Paso) Description: Interval uncertainty is closely related to fuzzy techniques: indeed, if we want to know how the fuzzy uncertainty of the inputs propagates through the data processing algorithm, then the usual Zadeh's extension principle is equivalent to processing alpha-cuts (intervals) for each level alpha. This relation between intervals and fuzzy computations is well known, but often, fuzzy researchers are unaware of the latest most efficient interval techniques and thus use outdated less efficient methods. One of the objectives of the proposed session is to help the fuzzy community by explaining the latest interval techniques and to help the interval community to better understand the related interval computation problems. Yet another relation between interval and fuzzy techniques is that the traditional fuzzy techniques implicitly assume that experts can describe their degree of certainty in different statements by an exact number. In reality, it is more reasonable to expect experts to provide only a rage (interval) of possible values -- leading to interval-valued fuzzy techniques that, in effect, combine both types of uncertainty. ************ The Joint NAFIPS International Conference on Fuzzy Systems, Soft Computing and Explainable AI and 10th World Conference on Soft Computing NAFIPS 2026 will be held in El Paso, Texas, USA, on March 14-16, 2026. https://sites.google.com/view/nafips26/ <venue> In 2025, we had a conference in Banff, Canada, on the Northern side of Rocky mountains. This year, this conference will be held in the southmost part of the same mountain range -- in El Paso, Texas. El Paso is among the ten safest cities in the US, It is a vibrant border city known for its unique blend of American and Mexican cultures, affordability, and historic charm. Located in far western Texas, the "Sun City" offers a high number of sunny days and is recognized for its beautiful desert landscapes and strong community spirit. El Paso is situated at the junction of Texas, New Mexico, and Mexico, creating a strong binational identity that influences its food, language (Spanglish is common), and festivals. The conference venue is the Art, Science, and Technology Building on the Valle Verde Campus of the El Paso Community College, see https://www.epcc.edu/Contact/about-the-campuses <Aims and Scope> As an international conference in the areas of fuzzy sets and soft computing, the NAFIPS 2026 conference will bring together scientists, engineers, students, and practitioners working in fuzzy logic and related areas to present their recent research accomplishments. The conference offers a unique platform for the exchange of ideas, fostering interaction and building multidisciplinary research linkages. <Topics> The topics cover all aspects of fuzzy systems and their applications including, but not limited to: * fuzzy sets and fuzzy logic * mathematical foundations of fuzzy sets and fuzzy systems * approximate reasoning, fuzzy inference models, and soft computing * fuzzy decision analysis, decision making, optimization, and design * fuzzy system architectures and hardware * fuzzy methods in data analysis, statistics and imprecise probability * fuzzy databases and information retrieval * fuzzy pattern recognition and image processing * fuzzy sets in management science * fuzzy control and robotics * possibility theory * fuzzy sets and logic in ontology, web, and social networks * fuzzy preference modeling * fuzzy sets in operations research and manufacturing * fuzzy database mining and financial forecasting * fuzzy neural networks * evolutionary and hybrid systems * intelligent agents and ambient intelligence * learning, adaptive, and evolvable fuzzy systems <Deadlines> Deadline for submitting tutorial and special session proposals: December 1, 2025 Deadline for paper submissions: December 1, 2025 Notification of acceptance: January 15, 2026 Deadline for final versions of accepted papers: February 15, 2026 Conference: March 14-16, 2026 <How to submit> Please submit your tutorial proposals to Marek Reformat, Tutorial Chair, by email to reformat(a)ualberta.ca<mailto:reformat@ualberta.ca>. Please submit your special session proposals to Fernando Gomide, Special Session Chair, at gomide(a)unicamp.br<mailto:gomide@unicamp.br>. Proposals for tutorials and special sessions should include the title, a short abstract, and the list of organizers (including a brief listing of their qualifications). Papers should be submitted via EasyChair, via a link https://easychair.org/my/conference?conf=nafips2026 If you are submitting to a special session, then when EasyChair asks you about the paper title, add - in capital letters - the session title before the title of your paper. For example, if you are submitting a paper titled "Our great revolutionary ideas for teaching and learning" to the special session on fuzzy education, then in the EasyChair slot for paper title write: "FUZZY EDUCATION Our great revolutionary ideas for teaching and learning". Also, in addition to submitting your papers to EasyChair, send a copy of your submission by email to the organizers of the special session. <Organizing committee> General Chair: Christian Servin (El Paso Community College) Program Chair: Scott Dick (University of Alberta, Canada) Special Sessions Chair: Fernando Gomide (University of Campinas, Brazil) Award Co-Chairs: Julia Rayz (Purdue University) Ildar Batyrshin (Instituto Politecnico Nacinal, Mexio) Tutorial Chair: Marek Reformat (University of Alberta, Canada) Industrial Liaison Chair: Kelly Cohen (University of Cincinnati) Competition Co-Chairs: Tim Arnett (Thales Flight Avionics, USA) Barnabas Bede (DigiPen University) Student and Young Researchers Chair: Wilhelm Louw (Pyramidion Co. and University of Cincinnati) Publicity Chair: Juan Carlos Figueroa-Garcia (Universita Distrital, Bogota, Colombia) Local Arrangements Co-Chairs: Christian Servin, Nadia Karichev, Ivan Alonso (El Paso Community College) Martine Ceberio, Vladik Kreinovich (University of Texas at El Paso)

1 0

FYI: IEEE Conference on AI
by Kreinovich, Vladik Nov. 15, 2025

Nov. 15, 2025

FYI, AI-related papers dealing with imprecise probabilities are always welcome at this series of conferences ************************* The 2026 IEEE Conference on Artificial Intelligence CAI 2026 Granada, Spain, May 8-10, 2026 https://sci2s.ugr.es/cai-2026 The 2026 IEEE Conference on Artificial Intelligence (IEEE CAI 2026) is the 4th Edition of the International Conference IEEE CAI that will take place in Granada (Spain). IEEE CAI 2026 is focused on the AI research and innovation with a special emphasis on the applications of AI and key AI verticals that impact industrial technology applications and innovations. You will learn about new research and breakthroughs in the industry, gain insight into new start-ups and leading AI companies, grow your network, and get inspired by the brightest minds working in the multi-faceted fields. IEEE CAI was previouly celebrated in Santa Clara (CAI 2023, 2025) and Singapore (CAI 2024) and it is supported by the important Technology IEEE Societies: IEEE Computational Intelligence Society, IEEE Computer Society, IEEE System, Man and Cybernetics Society and IEEE Signal Processing Society. Plan now to attend this highly anticipated spectacular event, taking place May 8-10, 2026 in Granada (Spain). Key AI Verticals: IEEE CAI 2026 offers an unprecedented experience with prominent AI speakers delivering keynote presentations, engaging workshops, technical and information sessions featuring contemporary AI topics, and insightful forward-looking panels around important sectors, which are related with the following key AI verticals: - Healthcare and Life Sciences. - Human-Robot Collaboration. - Sustainable and Trustworthy Ai. - Multimedia and Virtual Reality and Teleoperation. - Business Intelligence/ Finance. - Generative AI Models and Agentic AI. SUBMISSIONS & PUBLICATIONS: - See the web page of the conference. - The conference papers will be published according to the templates provided by IEEE eXpress Conference Publishing https://www.ieee.org/conferences/publishing/ieee-express-conference-publish… IMPORTANT DATES: Workshops, Tutorials, Panels, also Spec Sessions: October 15, 2025. Paper submission (all papers): November 30, 2025 Paper Evaluations to Authors: December 15, 2025. Final Camera Ready & Registration: January 20, 2026. Email contact: viedma(a)decsai.ugr.es<mailto:viedma@decsai.ugr.es> and rkozma(a)memphis.edu<mailto:rkozma@memphis.edu> General Chairs: * Enrique Herrera-Viedma, University of Granada, Granada, Spain, e-mail: viedma(a)decsai.ugr.es<mailto:viedma@decsai.ugr.es> * Robert Kozma, University of Memphis, USA e-mail: rkozma(a)memphis.edu<mailto:rkozma@memphis.edu> * Carmen Nestares, Amazon Prime, Seattle, USA Program Chairs: * Francisco Herrera, University of Granada, Granada, Spain, e-mail: herrera(a)decsai.ugr.es<mailto:herrera@decsai.ugr.es> * Giancarlo Fortino, University of Calabria, Italy, e-mail: g.fortino(a)unical.it<mailto:g.fortino@unical.it> * Bing Xue, Victoria University of Wellington, New Zealand, e-mail: Bing.Xue(a)vuw.ac.nz<mailto:Bing.Xue@vuw.ac.nz> * KC Santosh, University of South Dakota, South Daota, kc.santosh(a)usd.edu<mailto:kc.santosh@usd.edu> Honorary Chairs: * Piero Bonnisone, Piero P Bonnisone Analytics LLC * Fei-Yue Wang, Chinese Academy of Sciences * Bernadette Bouchon, Sorbonne Universite, Paris, France Advisory Board: * Hussein Abbass, University of New South Wales, Australia * Yew Soon Ong, Nanyang Technological University, Signapore * Marcos Lopez de Prada, Abu Dhabi Investment Authority (ADIA) * Ljiljana Trajkovic, Simon Fraser University, Canada * Saeid Nahavandi, Swinburne University of Technology, Australia * Adrian Stoica, USA Vice General Chairs: * Sam Kwong, Lingnan University, Hong Kong * Horst Simon, ADIA Lab, Abu Dhabi * Jie Lu, Sidney University of Technology Sydney, Australia * Carlos Coello, UNAM, Mexico Finance Chair: * Vladik Kreinovich, University of Texas at El Paso, USA Local Organizing Chairs: * Jose Luis Verdegay, University of Granada. * Oscar Cordon, University of Granada. * Manuel Jesus Cobo, University of Granada. * Sergio Alonso, University of Granada. Program committee: See in the web page of the conference.

1 0

3 years Postdoc position at TCD (Dublin) on Security & Privacy of unused parameters of ML models.
by Alessio Benavoli Oct. 29, 2025

Oct. 29, 2025

Dear colleagues and students, I am recruiting a Postdoctoral researcher with a background in game theoretic modelling, learning theory and both the theoretical and practical aspects of deep learning. The successful applicant will collaborate within a skilled and motivated team of scientists (from Trinity College Dublin, Queen's University Belfast and University California Riverside) dedicated to understand the security and privacy implications of the unused parameters present in machine learning models. The proposed research explores the problem both from the theoretical and empirical perspectives. *Description*: Machine Learning applications increasingly rely on Deep Neural Networks (DeepNNs) to achieve state-of-the-art performance across a wide range of real-world tasks, including Large Language Models. DeepNNs are typically highly over-parameterised, but this characteristic has been shown to facilitate both optimisation and generalisation. Nevertheless, such over-parameterisation also introduces many parameters that are not essential to the final learned model and whose specific values have little impact on its behaviour (don’t-care states). In both software and hardware systems, undefined behaviour and don’t-care states have been shown to be potential sources of vulnerabilities. The postdoc will conduct research that contributes to the following streams of work: 1) Investigate the possible strategies that colluding parties could use to maliciously exploit the unused parameters (learning capacity) of a machine learning model using techniques from information and learning theory; 2) Model the attacks within a game-theoretic framework under complete or incomplete knowledge (Bayesian games), which will enable to find optimal strategies for the players (Attacker, Nature and Defender); 3) Validate these theoretical models and strategies on machine learning models and real applications. Applications from candidates with expertise in *imprecise** Statistics or imprecise Machine Learning* are welcome. - For informal *inquiries* please contact *alessio.benavoli(a)tcd.ie <alessio.benavoli(a)tcd.ie>* - *Salary* is up to ~€71,000 per annum per 3 years. - *Start*: January 2026. - For additional details (including qualifications, knowledge/experience and how to apply)* see attached document.* Best regards, Alessio Benavoli

1 0

CFP IPMU 2026- Special Session on Theoretical and applied aspects of Imprecise Probabilities
by IGNACIO MONTES GUTIERREZ Oct. 18, 2025

Oct. 18, 2025

Dear colleagues, Please find attached a CFP for a special session on IP at the IPMU 2026 Conference, which will be held in Rome in June 2026. Best regards Ignacio Montes ****************************************************** [Apologise for multiple copies] Call for papers Special Session on "THEORETICAL AND APPLIED ASPECTS OF IMPRECISE PROBABILITIES" to be held at the 21st International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 2026) https://www.sbai.uniroma1.it/conferenze/ipmu2026/index.php Rome (Italy), June 15-19, 2026 Session topic and goal This session is devoted to Imprecise Probability Theory, which involves all the mathematical models that can be used as more flexible tools than usual Probability Theory when the available information is scarce, vague or incomplete. It includes lower previsions, n-monotone capacities, belief functions, p-boxes, possibility measures, or non-additive measures, among others. This special session aims to include papers related to Imprecise Probabilities that either present a significant advance in the foundations or show potential applications in real problems. In addition, papers where the connection between imprecise probability theories and other fields such as fuzzy sets or game theory is emphasised are also welcome. Theoretical topics of interest include (but are not limited to): * (coherent) uncertainty models * non-additive set-functions * qualitative reasoning about uncertainty * limit laws for imprecise probabilities * philosophical foundations * elicitation and inference * robust statistics * decision making Applications include (but are not limited to): * data mining * classification and machine learning * risk and reliability analysis * finance * life sciences * system control and design * algorithmic issues Dates Paper submission: January 12, 2026 Notification of Acceptance: February 15, 2026 Conference: June 15-19, 2026 Organisers We would be grateful if you could let us know whether you plan to submit a paper to this session. Any questions or remarks can be addressed to: David Nieto-Barba (nietodavid(a)uniovi.es) University of Oviedo (Spain) Ignacio Montes (imontes(a)uniovi.es) University of Oviedo (Spain)

1 0

Reminder: SIPTA seminar at 3pm Paris time
by sdesterc Oct. 17, 2025

Oct. 17, 2025

Dear Siptians, This a small reminder that our seminar is bound to start in a bit more than one hour. Milan Studeny will talk of “Combinatorial description of facets of the cone of exact games (or coherent lower probabilities)”. Zoom link is https://utc-fr.zoom.us/j/85055146633 Best regards Sébastien -- ==================================== Sebastien Destercke, Ph. D. CNRS researcher in computer science. Université de Technologie de Compiegne U.M.R. C.N.R.S. 7253 Heudiasyc Avenue de Landshut F-60205 Compiegne Cedex FRANCE Tel: +33 (0)3 44 23 79 85 Fax: +33 (0)3 44 23 44 77 ====================================

1 0

CNRS positions - reminder
by sdesterc Oct. 16, 2025

Oct. 16, 2025

Dear colleagues, As each year, the CNRS (centre national de recherche scientifique) will hire a number of people that will work in one of its associated laboratories (nation-wide in France), requiring candidates to provide a research project as well as a list of possible laboratories (associated to CNRS) in France where they could perform the proposed research. * Why should you apply? - CNRS positions are full permanent research positions that are, to my knowledge, one of the most flexible in terms of how you do your research. - CNRS offers quite a lot of opportunities (e.g., international labs) in case you want to make long foreign stays or develop your research into a product at some point. - As a CNRS researcher, you are mostly free to join any joint CNRS lab. This means that moving within France is very easy. - The institute is committed (and I can tell that by experience) to perform qualitative rather than quantitative assessments. So no obligation to publish or perish to prosper, but you can still play the game if you want. * Why should you not apply? - The salary is a priority for you: while it is quite decent at the start and quickly increases (in a rather predictable manner, as for all French state employees), it is probably below the level of tenured people in other European countries, notably due to the fact that France has historically chosen to have a lot of permanent public researchers/lecturers/professors (so monetary means are not concentrated nor subject to competition between universities). There is a number of ways to increase it (work part-time in company, give hours of teaching, providing some expertise, having salary supplements within projects), but most take some time away from research. - Learning French is not an option for you: while CNRS hires on a very regular basis non-french speaking researchers, daily life in France is definitely much more difficult if you do not have a working French. This can typically be acquired within some years (or maybe less) after arrival. * How should you apply? - Calendar: application files are typically to be submitted around January, with interviews in May. In order to prepare the candidacy, it is advisable to take contact with prospective teams/laboratories in October, November at the latest (preparing the application files take quite some time, and should be done in coordination at least with your preferred team) - Application file: It consists of a CV, a research statement (of about 10 pages in average), and of a research project that explains your scientific project for the next 5/10 years, understandable for specialist of the section you apply to (in computer science, the committee includes people from artificial intelligence, quantum computing, logic, mathematical programming, …). Within the project must be given three CNRS laboratories and teams (to be selected by the candidate among all the possible ones) in which you would like to perform this project. - Contacting laboratories/teams: if you have a laboratory/team you would like to join in case you are selected by CNRS, you should contact it as soon as possible. If you are interested or if you think of someone that could be interested, I will be happy to answer further questions, for instance to recommend labs where you could apply depending on your research project. Best regards Sébastien

1 0