collaborators

8 papers

cs.LG2026

Free-Probability Kernels for Zero-Rollout Hyperparameter Selection in Reservoir Computing

Sara Malacarne, Andrea Ceni, Claudio Gallicchio

Reservoir computing (RC) couples a fixed recurrent dynamical system with a trained lightweight readout, but this efficiency is partly lost during hyperparameter selection: the recu…

cs.LG2026

Frequency Domain Reservoir Computing

Klaus Schertler, Xiomara Runge, Andrea Ceni +2

While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requires architectures that balan…

cs.LG2026

ParalESN: Enabling parallel information processing in Reservoir Computing

Matteo Pinna, Giacomo Lagomarsini, Andrea Ceni +1

Reservoir Computing (RC) has established itself as an efficient paradigm for temporal processing. However, its scalability remains severely constrained by the need to process tempo…

cs.LG2026

Residual Reservoir Memory Networks

Matteo Pinna, Andrea Ceni, Claudio Gallicchio

We introduce a novel class of untrained Recurrent Neural Networks (RNNs) within the Reservoir Computing (RC) paradigm, called Residual Reservoir Memory Networks (ResRMNs). ResRMN c…

cs.LG2026

Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling

Andrea Ceni, Alessio Gravina, Claudio Gallicchio +3

The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, exi…

cs.NE2026

Scalable Memristive-Friendly Reservoir Computing for Time Series Classification

Coşku Can Horuz, Andrea Ceni, Claudio Gallicchio +1

Memristive devices present a promising foundation for next-generation information processing by combining memory and computation within a single physical substrate. This unique cha…