estimation

Minimax Estimation and Identity Testing of Markov Chains

Geoffrey Wolfer / 2022-09-18

We briefly review the two classical problems of distribution estimation and identity testing (in the context of property testing), then propose to extend them to a Markovian setting. We will see that the sample complexity depends not only on the number of states, but also on the stationary and…

webinars

Theory and Methods for Inference in Multi-armed Bandit Problems

2022-04-19

Theory and Methods for Inference in Multi-armed Bandit Problems Multi-armed bandit (MAB) algorithms have been argued for decades as useful to conduct adaptively-randomized experiments. By skewing the allocation of the arms towards the more efficient or informative ones, they have the potential to…

causal-inference

Heterogeneous Treatment Effects with Instrumental Variables: A Causal Machine Learning Approach

Falco J. Bargagli Stoffi / 2021-12-06

In our forthcoming paper on Annals of Applied Statistics, we propose a new method – which we call Bayesian Causal Forest with Instrumental Variable (BCF-IV) – to interpretably discover the subgroups with the largest or smallest causal effects in an instrumental variable setting. These are many…

webinars

Concentration Inequalities in Machine Learning

2021-06-30

The fifth “One World webinar” organized by YoungStatS will take place on September 15th, 2021. Selected young European researchers active in the areas of probability and machine learning will present their recent contributions. The webinar is joint cooperation between the Young Researchers Committee…

machine-learning

A small step to understand Generative Adversarial Networks

Gérard Biau, Benoît Cadre, Maxime Sangnier and Ugo Tanielian / 2021-04-27

In the last decade, there have been spectacular advances on the practical side of machine learning. One of the most impressive may be the success of Generative Adversarial Networks (GANs) for image generation (Goodfellow et al. 2014). State of the art models are capable of producing portraits of…

machine-learning

Analysis of a Two-Layer Neural Network via Displacement Convexity

Adel Javanmard, Marco Mondelli and Andrea Montanari / 2021-03-14

We consider the problem of learning a function defined on a compact domain, using linear combinations of a large number of “bump-like” components (neurons). This idea lies at the core of a variety of methods from two-layer neural networks to kernel regression, to boosting. In general, the resulting…