no code implementations • 10 Feb 2025 • Mélissa Tamine, Benjamin Heymann, Patrick Loiseau, Maxime Vono
Semivalue-based data valuation in machine learning (ML) quantifies the contribution of individual data points to a downstream ML task by leveraging principles from cooperative game theory and the notion of utility.
no code implementations • 12 Mar 2024 • Simon Finster, Patrick Loiseau, Simon Mauras, Mathieu Molina, Bary Pradelski
We initiate the study of how auction design affects the division of surplus among buyers.
no code implementations • NeurIPS 2023 • Mathieu Molina, Nicolas Gast, Patrick Loiseau, Vianney Perchet
We consider the problem of online allocation subject to a long-term fairness penalty.
no code implementations • 3 Jun 2023 • Felipe Garrido-Lucero, Benjamin Heymann, Maxime Vono, Patrick Loiseau, Vianney Perchet
We consider the dataset valuation problem, that is, the problem of quantifying the incremental gain, to some relevant pre-defined utility of a machine learning task, of aggregating an individual dataset to others.
1 code implementation • 12 Jun 2022 • Mathieu Molina, Patrick Loiseau
Then, we prove bounds (easily computable through marginal fairness and other meaningful statistical quantities) in high-probability on intersectional fairness in the general case.
no code implementations • 16 May 2022 • Till Kletti, Jean-Michel Renders, Patrick Loiseau
We lay out the structure of a new geometrical object (the DBN-expohedron), and propose for it a Carath\'eodory decomposition algorithm of complexity $O(n^3)$, where $n$ is the number of documents to rank.
1 code implementation • 7 Feb 2022 • Till Kletti, Jean-Michel Renders, Patrick Loiseau
Such a decomposition makes it possible to express any feasible target exposure as a distribution over at most $n$ rankings.
no code implementations • 10 Dec 2021 • Vitalii Emelianov, Nicolas Gast, Krishna P. Gummadi, Patrick Loiseau
In the second setting (with known variances), imposing the $\gamma$-rule decreases the utility but we prove a bound on the utility loss due to the fairness mechanism.
no code implementations • 28 Jun 2021 • Patrick Loiseau, Benjamin Roussillon
We consider the problem of finding optimal classifiers in an adversarial setting where the class-1 data is generated by an attacker whose objective is not known to the defender -- an aspect that is key to realistic applications but has so far been overlooked in the literature.
no code implementations • 24 Jun 2020 • Vitalii Emelianov, Nicolas Gast, Krishna P. Gummadi, Patrick Loiseau
We then compare the utility obtained by imposing a fairness mechanism that we term $\gamma$-rule (it includes demographic parity and the four-fifths rule as special cases), to that of a group-oblivious selection algorithm that picks the candidates with the highest estimated quality independently of their group.
no code implementations • 19 Nov 2019 • Dong Quan Vu, Patrick Loiseau, Alonso Silva, Long Tran-Thanh
Resource allocation games such as the famous Colonel Blotto (CB) and Hide-and-Seek (HS) games are often used to model a large variety of practical problems, but only in their one-shot versions.
Computer Science and Game Theory
1 code implementation • NeurIPS 2019 • Sarath Yasodharan, Patrick Loiseau
We study nonzero-sum hypothesis testing games that arise in the context of adversarial classification, in both the Bayesian as well as the Neyman-Pearson frameworks.
1 code implementation • 15 Jun 2019 • Vitalii Emelianov, George Arvanitakis, Nicolas Gast, Krishna Gummadi, Patrick Loiseau
In particular, our experiments show that the price of local fairness is generally smaller when the sensitive attribute is observed at the first stage; but globally fair selections are more locally fair when the sensitive attribute is observed at the second stage---hence in both cases it is often possible to have a selection that has a small price of local fairness and is close to locally fair.
2 code implementations • 27 May 2019 • Dong Quan Vu, Patrick Loiseau, Alonso Silva, Long Tran-Thanh
Resource allocation games such as the famous Colonel Blotto (CB) and Hide-and-Seek (HS) games are often used to model a large variety of practical problems, but only in their one-shot versions.
1 code implementation • 16 Mar 2016 • Vijay Kamble, Patrick Loiseau, Jean Walrand
We describe an approximate dynamic programming (ADP) approach to compute approximations of the optimal strategies and of the minimal losses that can be guaranteed in discounted repeated games with vector-valued losses.
1 code implementation • 30 Sep 2013 • Nicolas Gast, Stratis Ioannidis, Patrick Loiseau, Benjamin Roussillon
In this paper, we study a setting in which features are public but individuals choose the precision of the outputs they reveal to an analyst.