Research

We leverage social choice theory to propose a new procedure to rank systems based on their performance across different tasks.

This paper introduces a new methodology to learn from biased data, based on the generalized moment method.

We propose a methodology addressing the problem of outlier detection, by learning a data-driven scoring function defined on the feature space which reflects the degree of abnormality of the observations.

We review practical challenges in building and deploying ethical AI at the scale of contemporary industrial and societal uses.

We introduce a new feature importance method and apply it in the context of Wealth Management Compliance.

We review the recent technical literature in XAI and we propose actionable next steps.

Practical issues surrounding model development, from design complexities to the shortage of tools.

New upper bound to the mutual information between an attribute and the latent code of an encoder.

We leverage social choice theory to propose a new procedure to rank systems based on their performance across different tasks.

This paper introduces a new methodology to learn from biased data, based on the generalized moment method.

We propose a methodology addressing the problem of outlier detection, by learning a data-driven scoring function defined on the feature space which reflects the degree of abnormality of the observations.