no code implementations • 1 Dec 2023 • Antonio Sabbatella, Andrea Ponti, Antonio Candelieri, Ilaria Giordani, Francesco Archetti
In this paper we propose a Bayesian optimization method, executed in a continuous em-bedding of the combinatorial space.
no code implementations • 15 May 2023 • Antonio Candelieri
Gaussian Process based Bayesian Optimization is a well-known sample efficient sequential strategy for globally optimizing black-box, expensive, and multi-extremal functions.
1 code implementation • 2 Dec 2022 • Antonio Candelieri, Andrea Ponti, Francesco Archetti
Gaussian Process regression is a kernel method successfully adopted in many real-life applications.
no code implementations • 12 Oct 2022 • Antonio Candelieri, Andrea Ponti, Francesco Archetti
In this paper we propose (i) an extension of the optimal resource allocation to a more general class of problems, specifically with resources availability changing over time, and (ii) Bayesian Optimization as a more efficient alternative to SBF.
no code implementations • 18 May 2022 • Antonio Candelieri, Andrea Ponti, Francesco Archetti
There is a consensus that focusing only on accuracy in searching for optimal machine learning models amplifies biases contained in the data, leading to unfair predictions and decision supports.
no code implementations • 12 Dec 2021 • Antonio Candelieri, Andrea Ponti, Francesco Archetti
A distance from the Pareto frontier determines whether a choice is Pareto rational.
no code implementations • 22 Oct 2021 • Alessandro Riboni, Nicolò Ghioldi, Antonio Candelieri, Matteo Borrotti
Automated driving systems (ADS) have undergone a significant improvement in the last years.
1 code implementation • EACL 2021 • Silvia Terragni, Elisabetta Fersini, Bruno Giovanni Galuzzi, Pietro Tropeano, Antonio Candelieri
In this paper, we present OCTIS, a framework for training, analyzing, and comparing Topic Models, whose optimal hyper-parameters are estimated using a Bayesian Optimization approach.
no code implementations • 8 Mar 2021 • Antonio Candelieri, Andrea Ponti, Francesco Archetti
A bi-objective formalization is proposed: minimizing the average MDT and its standard deviation, that is the risk to detect some contamination event too late than the average MDT.
no code implementations • 9 Feb 2021 • Antonio Candelieri, Francesco Archetti
This paper addresses black-box optimization over multiple information sources whose both fidelity and query cost change over the search space, that is they are location dependent.
no code implementations • 5 Feb 2021 • Antonio Candelieri, Andrea Ponti, Francesco Archetti
The main objective of this paper is to outline a theoretical framework to analyse how humans' decision-making strategies under uncertainty manage the trade-off between information gathering (exploration) and reward seeking (exploitation).
no code implementations • 25 Jun 2020 • Antonio Candelieri, Riccardo Perego, Francesco Archetti
Computational results are reported related to the optimization of the hyperparameters of a Support Vector Machine (SVM) classifier using two sources: a large dataset - the most expensive one - and a smaller portion of it.
no code implementations • 9 Mar 2020 • Antonio Candelieri, Ilaria Giordani, Riccardo Perego, Francesco Archetti
This ap-proach makes more efficient the learning/updating of the probabilistic surrogate model and allows an efficient optimization of the acquisition function.
no code implementations • 9 Mar 2020 • Antonio Candelieri, Riccardo Perego, Ilaria Giordani, Andrea Ponti, Francesco Archetti
Modelling human function learning has been the subject of in-tense research in cognitive sciences.
no code implementations • 15 Aug 2019 • Yaroslav D. Sergeyev, Antonio Candelieri, Dmitri E. Kvasov, Riccardo Perego
The notion "safe" means that the objective function $f(x)$ during optimization should not violate a "safety" threshold, for instance, a certain a priori given value $h$ in a maximization problem.
no code implementations • 11 Jun 2019 • Antonio Candelieri, Stanislav Fedorov, Enza Messina
This paper presents an efficient approach for subsequence search in data streams.
no code implementations • 9 Nov 2018 • Stanislav Fedorov, Antonio Candelieri
On the basis of the known part of the model, a safe set in which the system can learn safely, the algorithm can choose optimal actions for pursuing the target set as long as the safety-preserving condition is satisfied.