no code implementations • 1 Feb 2024 • Francisco Daunas, Iñaki Esnaola, Samir M. Perlaza, H. Vincent Poor
The solution to empirical risk minimization with $f$-divergence regularization (ERM-$f$DR) is presented under mild conditions on $f$.
no code implementations • 19 Dec 2023 • Xinying Zou, Samir M. Perlaza, Iñaki Esnaola, Eitan Altman
Fundamental generalization metrics, such as the sensitivity of the expected loss, the sensitivity of the empirical risk, and the generalization gap are shown to have closed-form expressions involving the worst-case data-generating probability measure.
no code implementations • 21 Jun 2023 • Samir M. Perlaza, Iñaki Esnaola, Gaetan Bisson, H. Vincent Poor
The dependence on training data of the Gibbs algorithm (GA) is analytically characterized.
no code implementations • 12 Jun 2023 • Francisco Daunas, Iñaki Esnaola, Samir M. Perlaza, H. Vincent Poor
The analysis of the solution unveils the following properties of relative entropy when it acts as a regularizer in the ERM-RER problem: i) relative entropy forces the support of the Type-II solution to collapse into the support of the reference measure, which introduces a strong inductive bias that dominates the evidence provided by the training data; ii) Type-II regularization is equivalent to classical relative entropy regularization with an appropriate transformation of the empirical risk function.
no code implementations • 12 Nov 2022 • Samir M. Perlaza, Gaetan Bisson, Iñaki Esnaola, Alain Jean-Marie, Stefano Rini
Among these properties, the solution to this problem, if it exists, is shown to be a unique probability measure, mutually absolutely continuous with the reference measure.
no code implementations • 4 Nov 2022 • Xiuzhen Ye, Iñaki Esnaola, Samir M. Perlaza, Robert F. Harrison
A novel metric that describes the vulnerability of the measurements in power systems to data integrity attacks is proposed.
no code implementations • 3 Nov 2022 • Ke Sun, Samir M. Perlaza, Alain Jean-Marie
In this paper, $2\times2$ zero-sum games are studied under the following assumptions: $(1)$ One of the players (the leader) commits to choose its actions by sampling a given probability measure (strategy); $(2)$ The leader announces its action, which is observed by its opponent (the follower) through a binary channel; and $(3)$ the follower chooses its strategy based on the knowledge of the leader's strategy and the noisy observation of the leader's action.
no code implementations • 14 Jul 2022 • Xiuzhen Ye, Iñaki Esnaola, Samir M. Perlaza, Robert F. Harrison
The result of computing the VuIx of the measurements in the system yields an ordering of the measurements vulnerability based on the level of exposure to data integrity attacks.
no code implementations • 9 Feb 2022 • Samir M. Perlaza, Gaetan Bisson, Iñaki Esnaola, Alain Jean-Marie, Stefano Rini
The optimality and sensitivity of the empirical risk minimization problem with relative entropy regularization (ERM-RER) are investigated for the case in which the reference is a sigma-finite measure instead of a probability measure.
no code implementations • 31 Dec 2021 • Xiuzhen Ye, Iñaki Esnaola, Samir M. Perlaza, Robert F. Harrison
Sparse stealth attack constructions that minimize the mutual information between the state variables and the observations are proposed.
no code implementations • 6 Jul 2020 • Xiuzhen Ye, Iñaki Esnaola, Samir M. Perlaza, Robert F. Harrison
The attack construction is formulated as an optimization problem that aims to minimize the mutual information between the state variables and the observations while guaranteeing the stealth of the attack.