no code implementations • 8 Oct 2024 • Nicolas Gast, Dheeraj Narasimha
Our solution requires minimal assumptions and quantifies the loss in optimality in terms of $\tau$ and the number of arms, $N$.
1 code implementation • 23 May 2024 • Sebastian Allmeier, Nicolas Gast
Furthermore, we show that the time-averaged bias is equal to $\alpha V + O(\alpha^2)$, where $V$ is a constant characterized by a Lyapunov equation, showing that $\mathbb{E}[\bar{\theta}_n] \approx \theta^*+V\alpha + O(\alpha^2)$, where $\bar{\theta}_n=(1/n)\sum_{k=1}^n\theta_k$ is the Polyak-Ruppert average.
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 • 13 Jan 2023 • Romain Cravic, Nicolas Gast, Bruno Gaujal
We propose the first model-free algorithm that achieves low regret performance for decentralized learning in two-player zero-sum tabular stochastic games with infinite-horizon average-reward objective.
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 • 16 Jun 2021 • Nicolas Gast, Bruno Gaujal, Kimang Khun
While the regret bound and runtime of vanilla implementations of PSRL and UCRL2 are exponential in the number of bandits, we show that the episodic regret of MB-PSRL and MB-UCRL2 is $\tilde{O}(S\sqrt{nK})$ where $K$ is the number of episodes, $n$ is the number of bandits and $S$ is the number of states of each bandit (the exact bound in S, n and K is given in the paper).
no code implementations • 16 Dec 2020 • Nicolas Gast, Bruno Gaujal, Chen Yan
In this paper we show that, under the same conditions, the convergence rate is exponential in the number of bandits, unless the fixed point is singular (to be defined later).
Performance Optimization and Control Probability
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.
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.
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.