181 citations · 352 across the 20 of their papers we have counts for
22 papers
Density-Ratio Losses for Post-Hoc Learning to Defer
Alexander Soen, Ragnar Thobaben, Joakim Jaldén +1
We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions: divergence-regularized reweightings of the data distribution under which a model attains low loss…
A Hierarchical Sampling Framework for bounding the Generalization Error of Federated Learning
Dario Filatrella, Ragnar Thobaben, Mikael Skoglund
We study expected generalization bounds for the Hierarchical Federated Learning (HFL) setup using Wasserstein distance. We introduce a generalized framework in which data is sample…
Information-Theoretic Fairness with A Bounded Statistical Parity Constraint
Amirreza Zamani, Abolfazl Changizi, Ragnar Thobaben +1
In this paper, we study an information-theoretic problem of designing a fair representation that attains bounded statistical (demographic) parity. More specifically, an agent uses…
A Coding-Theoretic Analysis of Hyperspherical Prototypical Learning Geometry
Martin Lindström, Borja Rodríguez-Gálvez, Ragnar Thobaben +1
Hyperspherical Prototypical Learning (HPL) is a supervised approach to representation learning that designs class prototypes on the unit hypersphere. The prototypes bias the repres…
A note on generalization bounds for losses with finite moments
Borja Rodríguez-Gálvez, Omar Rivasplata, Ragnar Thobaben +1
This paper studies the truncation method from Alquier [1] to derive high-probability PAC-Bayes bounds for unbounded losses with heavy tails. Assuming that the -th moment is boun…
More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity
Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund
In this paper, we present new high-probability PAC-Bayes bounds for different types of losses. Firstly, for losses with a bounded range, we recover a strengthened version of Catoni…