239 citations · 772 across the 73 of their papers we have counts for
79 papers
Fantastic Generalization Measures are Nowhere to be Found
Michael Gastpar, Ido Nachum, Jonathan Shafer +1
We study the notion of a generalization bound being uniformly tight, meaning that the difference between the bound and the population loss is small for all learning algorithms and…
Lower Bounds on the Bayesian Risk via Information Measures
Amedeo Roberto Esposito, Adrien Vandenbroucque, Michael Gastpar
This paper focuses on parameter estimation and introduces a new method for lower bounding the Bayesian risk. The method allows for the use of virtually \emph{any} information measu…
Generalization Error Bounds for Noisy, Iterative Algorithms via Maximal Leakage
Ibrahim Issa, Amedeo Roberto Esposito, Michael Gastpar
We adopt an information-theoretic framework to analyze the generalization behavior of the class of iterative, noisy learning algorithms. This class is particularly suitable for stu…
Finite Littlestone Dimension Implies Finite Information Complexity
Aditya Pradeep, Ido Nachum, Michael Gastpar
We prove that every online learnable class of functions of Littlestone dimension admits a learning algorithm with finite information complexity. Towards this end, we use the no…
From Generalisation Error to Transportation-cost Inequalities and Back
Amedeo Roberto Esposito, Michael Gastpar
In this work, we connect the problem of bounding the expected generalisation error with transportation-cost inequalities. Exposing the underlying pattern behind both approaches we…
On Sibson's -Mutual Information
Amedeo Roberto Esposito, Adrien Vandenbroucque, Michael Gastpar
We explore a family of information measures that stems from Rényi's -Divergences with . In particular, we extend the definition of Sibson's -Mutual Information to negati…