no code implementations • 1 Sep 2022 • Solenne Gaucher, Nicolas Schreuder, Evgenii Chzhen
In the awareness framework, akin to the classical unconstrained classification case, we show that maximizing accuracy under this fairness constraint is equivalent to solving a corresponding regression problem followed by thresholding at level $1/2$.
no code implementations • 18 Mar 2022 • Solenne Gaucher, Alexandra Carpentier, Christophe Giraud
We also derive gap-dependent upper bounds on the regret, and matching lower bounds for some problem instance. Interestingly, these results reveal a transition between a regime where the problem is as difficult as its unbiased counterpart, and a regime where it can be much harder.
no code implementations • NeurIPS 2021 • Solenne Gaucher, Olga Klopp
This provides the first minimax optimal and tractable estimator for the problem of parameter estimation for the stochastic block model with missing links.
1 code implementation • 16 Nov 2021 • Anestis Antoniadis, Solenne Gaucher, Yannig Goude
The recent abundance of data on electricity consumption at different scales opens new challenges and highlights the need for new techniques to leverage information present at finer scales in order to improve forecasts at wider scales.
no code implementations • NeurIPS 2020 • Solenne Gaucher
Under natural assumptions on the reward function, we prove that the optimal regret scales as $O(T^{1/3})$ up to poly-logarithmic factors when the budget $T$ is proportional to the number of actions $N$.
no code implementations • 29 Nov 2019 • Solenne Gaucher, Olga Klopp, Geneviève Robin
The proposed method is statistically sound: we prove that, under fairly general assumptions, our algorithm exactly detects the outliers, and achieves the best known error for the prediction of missing links with polynomial computation cost.