collaborators

8 papers

cs.LG2026

Incremental Gauss-Newton Descent for Machine Learning

Mikalai Korbit, Mario Zanon

Stochastic gradient updates are widely used for their efficiency and scalability, but their effective step sizes can depend strongly on feature scaling and local model sensitivity.…

eess.SY2026

Active Learning MPC Objective Functions from Preferences

Hasna El Hasnaouy, Pablo Krupa, Mario Zanon +1

Designing the objective function in Model Predictive Control (MPC) is challenging when performance assessment criteria are available only from human judgment. We adopt a preference…

cs.LG2026

Fast Gauss-Newton for Multiclass Cross-Entropy

Mikalai Korbit, Mario Zanon

In multiclass softmax cross-entropy, the full generalized Gauss-Newton (GGN) curvature couples all output logits through the softmax covariance, making curvature-vector products ha…

cs.LG2026

Second-Order, First-Class: A Composable Stack for Curvature-Aware Training

Mikalai Korbit, Mario Zanon

Second-order methods promise improved stability and faster convergence, yet they remain underused due to implementation overhead, tuning brittleness, and the lack of composable API…

math.OC2026

On Two-Player Scalar Discrete-Time Linear Quadratic Games

Chiara Cavalagli, Alberto Bemporad, Mario Zanon

For the characterization of Feedback Nash Equilibria (FNE) in linear quadratic games, this paper provides a detailed analysis of the discrete-time discounted coupled best-response…

eess.SY2025

Learning the MPC objective function from human preferences

Pablo Krupa, Hasna El Hasnaouy, Mario Zanon +1

In Model Predictive Control (MPC), the objective function plays a central role in determining the closed-loop behavior of the system, and must therefore be designed to achieve the…