Generalization Error Bounds Via Rényi-, f-Divergences and Maximal Leakage
Amedeo Roberto Esposito, Michael Gastpar, Ibrahim Issa
Published in IEEE Transactions on Information Theory Volume: 67, Issue: 8
Download here
Publications
Lower-bounds on the Bayesian Risk in estimation procedures via Sibson’s α-Mutual Information
Amedeo Roberto Esposito, Michael Gastpar
Published in 2021 IEEE International Symposium on Information Theory (ISIT)
Download here
On conditional Sibson’s α-Mutual Information
Amedeo Roberto Esposito, Diyuan Wu, Michael Gastpar
Published in 2021 IEEE International Symposium on Information Theory (ISIT)
Download here
Towards a Standard Testing Data Set in Privacy
Amedeo Roberto Esposito
Published in BCS Learning & Development
Download here
On Sibson’s α-Mutual Information
Amedeo Roberto Esposito, Adrien Vandenbroucque, Michael Gastpar
Published in 2022 IEEE International Symposium on Information Theory (ISIT)
Download here
Lower-bounds on the Bayesian Risk in Estimation Procedures via f–Divergences
Adrien Vandenbroucque, Amedeo Roberto Esposito, Michael Gastpar
Published in 2022 IEEE International Symposium on Information Theory (ISIT)
Download here
From Generalisation Error to Transportation-cost Inequalities and Back
Amedeo Roberto Esposito, Michael Gastpar
Published in 2022 IEEE International Symposium on Information Theory (ISIT)
Download here
Robust Generalization via f−Mutual Information
Amedeo Roberto Esposito, Michael Gastpar, Ibrahim Issa
Published in 2020 IEEE International Symposium on Information Theory (ISIT)
Download here
Robust Generalization via α-Mutuaaal Information
Amedeo Roberto Esposito, Michael Gastpar, Ibrahim Issa
Published in 2020 International Zurich Seminar on Information and Communication (IZS)
Download here
Learning and adaptive data analysis via maximal leakage
Amedeo Roberto Esposito, Michael Gastpar, Ibrahim Issa
Published in 2019 IEEE Information Theory Workshop (ITW)
Download here
Strengthened information-theoretic bounds on the generalization error
Ibrahim Issa, Amedeo Roberto Esposito, Michael Gastpar
Published in 2019 IEEE International Symposium on Information Theory (ISIT)
Download here