will give a presentation on

Abstract:

Topic models provide a useful tool to organize and understand the structure of large corpora of text documents, in particular, to discover hidden thematic structure. Clustering documents from big unstructured corpora into topics is an important task in various fields, such as image analysis, e-commerce, social networks, population genetics. Since the number of topics is typically substantially smaller than the size of the corpus and of the dictionary, the methods of topic modeling can lead to a dramatic dimension reduction. We study the problem of estimating the topic-document matrix, which gives the topics distribution for each document in a given corpus, that is we focus on the clustering aspect of the problem. We introduce an algorithm that we call Successive Projection Overlapping Clustering (SPOC) inspired by the Successive Projection Algorithm for separable matrix factorization. This algorithm is simple to implement and computationally fast. We establish upper bounds on the performance of SPOC algorithm for estimation of topic-document matrix, as well as near matching minimax lower bounds.

Timing : 14:30

Start date : Fri, 06 Oct 2023 00:00:00 +0200

Location : ISBA - C115 (1st Floor) Voie du Roman Pays 20

1348 Louvain-la-neuve

BE]]>

will give a presentation on

Abstract:

How much evidence do the data give us about one hypothesis versus another? The standard way to measure evidence is still the p-value, despite a myriad of problems surrounding it. We present the e-value, a recently popularized notion of evidence which overcomes some of these issues. While e-values were only given a name as recently as 2019, interest in them has since exploded with papers in the Annals, JRSS B, Biometrika and the like - June 2022 saw the first international workshop on e-values, a second one is planned for May 2024.

In simple cases, e-values coincide with Bayes factors. But if the null is composite or nonparametric, or an alternative cannot be explicitly formulated, e-values and Bayes factors become distinct and e-processes can be seen as a generalization of nonnegative supermartingales. Unlike the Bayes factor, e-values always allow for tests with strict frequentist Type-I error control under optional continuation of data collection and combination of data from different sources. E-values are also the basic building blocks of anytime-valid confidence intervals that remain valid under continuous monitoring and optional stopping. In parametric settings they tend to be strictly wider than, hence consistent with Bayesian credible intervals. This led to the development of the e-posterior, an analogue to the Bayesian posterior that *gets wider rather than wrong* if the prior is chosen badly.

This work is based on:

P. Grunwald,. R. de Heide, W. Koolen (2023). Safe Testing. To appear in J. Roy. Stat. Soc., Series B

P. Grunwald (2023) . The E-Posterior. Proc. Phil. Trans. Soc. London Series A, 2023.

Timing : 14:30

Start date : Fri, 13 Oct 2023 00:00:00 +0200

Location : ISBA - C115 (1st Floor)

1348 Louvain-la-neuve

BE]]>

We are happy to announce that the **30th Annual Meeting of the Royal Statistical Society of Belgium** will take place in Louvain-la-Neuve on **October 19 and 20, 2023 !** This edition of the annual meeting is **organized by UCLouvain** with the support of the Institute of Statistics, Biostatistics and Actuarial Sciences.

Program : Soon available

Timing : TBC

Website : More information

Start date : Thu, 19 Oct 2023 00:00:00 +0200

End date : Fri, 20 Oct 2023 00:00:00 +0200

Location : Hotel Ibis Styles Louvain-la-Neuve Bd de Lauzelle 61, 1348 Ottignies-Louvain-la-Neuve

1348 Louvain-la-Neuve

BE]]>

Will give a presentation on

Abstract:

In the first part of the talk we give a brief introduction to the concepts of *statistical depth* and *object data*. In summary, statistical depth measures assign high (low) values for points located near (far away from) the bulk of the data distribution, allowing quantifying their centrality/outlyingness. Whereas, object data refers to samples of data where the observations reside in an arbitrary metric space, instead of the space R^p.

In the second part of the talk we describe a novel measure of statistical depth, the metric spatial depth, for object data. This depth measure is shown to have highly interpretable geometric properties, making it appealing in object data analysis where standard descriptive statistics are difficult to compute. The proposed measure reduces to the classical spatial depth in a Euclidean space. In addition to studying its theoretical properties, to provide intuition on the concept, we explicitly compute metric spatial depths in several different metric spaces. Finally, we showcase the practical usefulness of the metric spatial depth in outlier detection, non-convex depth region estimation and classification.

Related preprint: https://arxiv.org/abs/2306.09740

Timing : 14:30

Start date : Fri, 03 Nov 2023 00:00:00 +0100

Location : ISBA - C115 (1st Floor) Voie du Roman Pays 20

1348 Louvain-la-neuve

BE]]>

Start date : Fri, 10 Nov 2023 00:00:00 +0100

Location : ISBA - C115 (1st Floor)

1348 Louvain-la-neuve

BE]]>