425 citations · 1.4k across the 81 of their papers we have counts for
7 papers · 1 filter
Generalization Bounds: Perspectives from Information Theory and PAC-Bayes
Fredrik Hellström, Giuseppe Durisi, Benjamin Guedj +1
A fundamental question in theoretical machine learning is generalization. Over the past decades, the PAC-Bayesian approach has been established as a flexible framework to address t…
Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness
Fredrik Hellström, Giuseppe Durisi
Recent work has established that the conditional mutual information (CMI) framework of Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees in t…
A New Family of Generalization Bounds Using Samplewise Evaluated CMI
Fredrik Hellström, Giuseppe Durisi
We present a new family of information-theoretic generalization bounds, in which the training loss and the population loss are compared through a jointly convex function. This func…
Transfer Meta-Learning: Information-Theoretic Bounds and Information Meta-Risk Minimization
Sharu Theresa Jose, Osvaldo Simeone, Giuseppe Durisi
Meta-learning automatically infers an inductive bias by observing data from a number of related tasks. The inductive bias is encoded by hyperparameters that determine aspects of th…
Fast-Rate Loss Bounds via Conditional Information Measures with Applications to Neural Networks
Fredrik Hellström, Giuseppe Durisi
We present a framework to derive bounds on the test loss of randomized learning algorithms for the case of bounded loss functions. Drawing from Steinke & Zakynthinou (2020), this f…
Conditional Mutual Information-Based Generalization Bound for Meta Learning
Arezou Rezazadeh, Sharu Theresa Jose, Giuseppe Durisi +1
Meta-learning optimizes an inductive bias---typically in the form of the hyperparameters of a base-learning algorithm---by observing data from a finite number of related tasks. Thi…