Anthony Bardou

selected publications

1. NeurIPS

   This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization

   Anthony Bardou, Patrick Thiran, and Giovanni Ranieri

   In NeurIPS’24: Thirty-Eighth Annual Conference on Neural Information Processing Systems 2024

   Abs Bib PDF Video

   Bayesian Optimization (BO) has proven to be very successful at optimizing a static, noisy, costly-to-evaluate black-box function f : \mathcalS \to \mathbbR. However, optimizing a black-box which is also a function of time (i.e., a dynamic function) f : \mathcalS \times \mathcalT \to \mathbbR remains a challenge, since a dynamic Bayesian Optimization (DBO) algorithm has to keep track of the optimum over time. This changes the nature of the optimization problem in at least three aspects: (i) querying an arbitrary point in \mathcalS \times \mathcalT is impossible, (ii) past observations become less and less relevant for keeping track of the optimum as time goes by and (iii) the DBO algorithm must have a high sampling frequency so it can collect enough relevant observations to keep track of the optimum through time. In this paper, we design a Wasserstein distance-based criterion able to quantify the relevancy of an observation with respect to future predictions. Then, we leverage this criterion to build W-DBO, a DBO algorithm able to remove irrelevant observations from its dataset on the fly, thus maintaining simultaneously a good predictive performance and a high sampling frequency, even in continuous-time optimization tasks with unknown horizon. Numerical experiments establish the superiority of W-DBO, which outperforms state-of-the-art methods by a comfortable margin.

   @inproceedings{wdbo,
     author = {Bardou, Anthony and Thiran, Patrick and Ranieri, Giovanni},
     booktitle = {NeurIPS'24: Thirty-Eighth Annual Conference on Neural Information Processing Systems},
     title = {This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization},
     year = {2024},
     video = {PermSix-Hump_Camel_25.0_240.mp4},
   }

2. ICLR

   Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization

   Anthony Bardou, Patrick Thiran, and Thomas Begin

   In ICLR ’24: Int’l Conference on Learning Representations 2024

   Abs Bib PDF

   Bayesian Optimization (BO) is typically used to optimize an unknown function f that is noisy and costly to evaluate, by exploiting an acquisition function that must be maximized at each optimization step. Even if provably asymptotically optimal BO algorithms are efficient at optimizing low-dimensional functions, scaling them to high-dimensional spaces remains an open problem, often tackled by assuming an additive structure for f. By doing so, BO algorithms typically introduce additional restrictive assumptions on the additive structure that reduce their applicability domain. This paper contains two main contributions: (i) we relax the restrictive assumptions on the additive structure of f \textitwithout weakening the maximization guarantees of the acquisition function, and (ii) we address the over-exploration problem for decentralized BO algorithms. To these ends, we propose DuMBO, an asymptotically optimal decentralized BO algorithm that achieves very competitive performance against state-of-the-art BO algorithms, especially when the additive structure of f comprises high-dimensional factors.

   @inproceedings{dumbo,
     author = {Bardou, Anthony and Thiran, Patrick and Begin, Thomas},
     booktitle = {ICLR '24: Int'l Conference on Learning Representations},
     title = {Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization},
     year = {2024},
   }

3. MSWiMBest Paper Award

   INSPIRE: Distributed Bayesian Optimization for ImproviNg SPatIal REuse in Dense WLANs

   Anthony Bardou, and Thomas Begin

   In MSWiM ’22: Int’l ACM Conference on Modeling Analysis and Simulation of Wireless and Mobile Systems 2022

   Abs Bib PDF

   WLANs, which have overtaken wired networks to become the primary means of connecting devices to the Internet, are prone to performance issues due to the scarcity of space in the radio spectrum. As a response, IEEE 802.11ax and subsequent amendments aim at increasing the spatial reuse of a radio channel by allowing the dynamic update of two key parameters in wireless transmission: the transmission power (TX_POWER) and the sensitivity threshold (OBSS_PD). In this paper, we present INSPIRE, a distributed online learning solution performing local Bayesian optimizations based on Gaussian processes to improve the spatial reuse in WLANs. INSPIRE makes no explicit assumptions about the topology of WLANs and favors altruistic behaviors of the access points, leading them to find adequate configurations of their TX_POWER and OBSS_PD parameters for the "greater good" of the WLANs. We demonstrate the superiority of INSPIRE over other state-of-the-art strategies using the ns-3 simulator and two examples inspired by real-life deployments of dense WLANs. Our results show that, in only a few seconds, INSPIRE is able to drastically increase the quality of service of operational WLANs by improving their fairness and throughput.

   @inproceedings{inspire,
     author = {Bardou, Anthony and Begin, Thomas},
     booktitle = {MSWiM '22: Int'l ACM Conference on Modeling Analysis and Simulation of Wireless and Mobile Systems},
     editor = {ACM},
     title = {INSPIRE: Distributed Bayesian Optimization for ImproviNg SPatIal REuse in Dense WLANs},
     year = {2022},
     bp = {},
   }