activity
20242026
collaborators

6 papers

eess.SY2026

Geometric SSM: LTI State Space Models for Selective Tasks

Umberto Casti, Giacomo Baggio, Sandro Zampieri +1

A key claim in recent work on Selective State Space Models is that selectivity, the ability to focus on relevant information while filtering irrelevant inputs, requires breaking th…

cs.LG2026

Context-Selective State Space Models: Feedback is All You Need

Riccardo Zattra, Giacomo Baggio, Umberto Casti +2

Transformers, powered by the attention mechanism, are the backbone of most foundation models, yet they suffer from quadratic complexity and difficulties in dealing with long-range…

math.OC2025

Anti-windup design for internal model online constrained optimization

Umberto Casti, Sandro Zampieri

This paper proposes a novel algorithmic design procedure for online constrained optimization grounded in control-theoretic principles. By integrating the Internal Model Principle (…

eess.SY2025

Controllable Neural Architectures for Multi-Task Control

Umberto Casti, Giacomo Baggio, Sandro Zampieri +1

This paper studies a multi-task control problem where multiple linear systems are to be regulated by a single non-linear controller. In particular, motivated by recent advances in…

math.OC2024

Stochastic models for online optimization

Umberto Casti, Sandro Zampieri

In this paper, we propose control-theoretic methods as tools for the design of online optimization algorithms that are able to address dynamic, noisy, and partially uncertain time-…

math.OC2024

A Control Theoretical Approach to Online Constrained Optimization

Umberto Casti, Nicola Bastianello, Ruggero Carli +1

In this paper we focus on the solution of online problems with time-varying, linear equality and inequality constraints. Our approach is to design a novel online algorithm by lever…