collaborators

12 papers

cs.LG2026

The Method of Gaps: Exact Expressions for the Generalization Error of Supervised Learning Algorithms

Samir M. Perlaza, Xinying Zou

In this paper, the method of gaps, a technique for deriving closed-form expressions in terms of information measures for the generalization error of supervised learning algorithms,…

stat.ML2026

Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms

Yaiza Bermudez, Samir M. Perlaza, Iñaki Esnaola

In this paper, it is shown, for the first time, that centralized performance is achievable in decentralized learning without sharing the local datasets. Specifically, when clients…

cs.IT2026

VLSF Decoding with Reliability Guarantees over Correlated Noncoherent Fading Channels

Guodong Sun, Samir M. Perlaza, Philippe Mary +1

This paper studies reliability-guaranteed decoding for variable-length stop-feedback (VLSF) codes over correlated noncoherent fading channels. The decoding rule is based on the evo…

cs.IT2026

Optimization of Sparse VLSF Codes for Short-Packet Transmission via Saddlepoint Methods

Guodong Sun, Samir M. Perlaza, Philippe Mary +1

In this work, we present an optimization framework for sparse variable-length stop-feedback (VLSF) codes based on a saddlepoint approximation, which jointly optimizes the decoding…

math.ST2026

Equivalence of optimal transport problems to regularization on the family of f-divergences

Maxime Nicaise, Yaiza Bermudez, Samir M. Perlaza

This work establishes that an optimal transport~(OT) problem regularized by a given -divergence admits the same solution as another OT problem regularized by a different -div…

cs.LG2026

On the Role of Reversible Instance Normalization

Gaspard Berthelier, Tahar Nabil, Etienne Le Naour +3

Data normalization is a crucial component of deep learning models, yet its role in time series forecasting remains insufficiently understood. In this paper, we identify three centr…