# SIPTA Seminars

Are you a curious student that has just started to explore the topic of imprecise probabilities?
Or an experienced researcher that would like to keep in touch with the community?
Join us at the *SIPTA Seminars*, an online series of seminars on imprecise probabilities (IP).
The seminars are open to anyone interested in IP, and are followed by a Q&A and open discussion.
They take place roughly once per month, with a break over the summer.
Topics range from foundational IP theories to applications that can benefit from IP approaches.

Details about the individual seminars are available in the list below. Close to the date of the next seminar, a zoom link will be provided there as well, which is freely accessible. If you click it, you will first be taken to a waiting room; please be patient until the organizers let you in. During the talk, questions should be put in the chat, and the audience is expected to mute their microphones. After the talk, there will be time for Q&A and discussion, at which point you can turn on your microphone when you want to contribute. The talk (but not the Q&A and discussion) will be recorded, and will afterwards be made freely available on the SIPTA Youtube channel.

The organisation is taken care of by Sébastien Destercke, Enrique Miranda and Jasper De Bock. If you have questions about the seminars, or suggestions for future speakers, you can get in touch with us at seminars@sipta.org. Suggestions for prominent speakers outside the IP community, whose work is nevertheless related to IP, are especially welcome.

## Upcoming Seminars

### Falsification, Fisher's underworld of probability, and balancing behavioral & statistical reliability

Ryan Martin 18 October 2023, 15:00 CESTZoom link: https://utc-fr.zoom.us/j/82973185259

Statisticians develop methods to assist in building probability statements that will be used to make inference on relevant unknowns. Popper argued that probability statements themselves can’t be falsified, but what about the statistical methods that use data to generate them? Science today is largely empirical, so if statistical methods’ conversion of data into scientific judgments can’t be scrutinized, then it’s not fair to expect society to “trust the science.”

Fisher’s underworld of probability concerns layers below the textbook surface level, where knowledge is vague and imprecise. Roughly, suppose that an agent quantifies his uncertainty about a relevant unknown via (imprecise) probability statements, which defines his betting odds. Now suppose that a second agent, who may not have her own probability statements about the relevant unknown, believes that the first agent’s assessments are wrong and can formulate odds at which she’d bet against the first agent’s wagers. If the second agent wins in these side-bets, then she reveals a shortcoming in the first agent’s assessments. I claim that the statistical method and “society” above are like the first and second agents here, respectively, and that scrutiny of a statistical method proceeds by giving “society” an opportunity to bet against its claims.

In this talk, I’ll carry out this scrutiny formally/mathematically and present some key take-aways. No surprise, a statistical method that’s falsification-proof in this sense is the behaviorally most reliable and conservative generalized Bayes rule. More surprising, however, is that a necessary condition for being falsification-proof is a statistical reliability property – called validity – that I’ve been advocating for recently. It follows, then, from the false confidence theorem that statistical methods quantifying uncertainty via precise probabilities can typically be falsified in this sense. More generally, since validity also implies certain behavioral reliability properties and needn’t be overly conservative, my new possibilistic inference framework (which I’ll describe and illustrate) is a promising way to balance the behavioral and statistical reliability properties.

There’s no paper yet on the exact contents of this talk, but some relevant material can be found at https://arxiv.org/abs/2203.06703 and https://arxiv.org/abs/2211.14567.

### Structural Causal Models are (Solvable by) Credal Networks

Alessandro Antonucci 28 November 2023, 15:00 CETZoom link: https://utc-fr.zoom.us/j/85152847934

### On the Interplay of Optimal Transport and Distributionally Robust Optimization

Daniel Kuhn 12 December 2023, 15:00 CETZoom link: https://utc-fr.zoom.us/j/82027992604

Optimal Transport (OT) seeks the most efficient way to morph one probability distribution into another one, and Distributionally Robust Optimization (DRO) studies worst-case risk minimization problems under distributional ambiguity. It is well known that OT gives rise to a rich class of data-driven DRO models, where the decision-maker plays a zero-sum game against nature who can adversely reshape the empirical distribution of the uncertain problem parameters within a prescribed transportation budget. Even though generic OT problems are computationally hard, the Nash strategies of the decision-maker and nature in OT-based DRO problems can often be computed efficiently. In this talk we will uncover deep connections between robustification and regularization, and we will disclose striking properties of nature’s Nash strategy, which implicitly constructs an adversarial training dataset. We will also show that OT-based DRO offers a principled approach to deal with distribution shifts and heterogeneous data sources, and we will highlight new applications of OT-based DRO in machine learning, statistics, risk management and control. Finally, we will argue that, while OT is useful for DRO, ideas from DRO can also help us to solve challenging OT problems.

## Past Seminars

### Application of uncertainty theory in the field of environmental risks

Dominique Guyonnet 27 September 2023, 15:00 CESTWatch on YouTube

### One way to define an imprecise-probabilistic version of the Poisson process

Alexander Erreygers 16 June 2023, 15:00 CESTWatch on YouTube

### Random fuzzy sets and belief functions: application to machine learning

Thierry Denœux 24 May 2023, 15:00 CESTWatch on YouTube

### Some finitely additive probabilities and decisions

Teddy Seidenfeld 17 February 2023, 15:00 CETWatch on YouTube

### Engineering and IP: what's going on?

Alice Cicirello, Matthias Faes & Edoardo Pattelli 13 January 2023, 15:00 CETWatch on YouTube

### Dealing with Uncertain Arguments in Artificial Intelligence

Fabio Cozman 29 November 2022, 15:00 CETWatch on YouTube

### Coalitional game theory vs Imprecise probabilities: Two sides of the same coin ... or not?

Ignacio Montes 21 October 2022, 15:00 CESTWatch on YouTube

### Imprecise probabilities in modern data science: challenges and opportunities

Ruobin Gong 29 June 2022, 15:00 CESTWatch on YouTube

### Imprecision, not as a problem, but as part of the solution

Gert de Cooman 30 May 2022, 15:00 CESTWatch on YouTube