activity
20242026
collaborators

9 papers

math.AG2026

Rigidity for Lie algebras of locally finite derivations

Mohamed Ali Belabbas

Let be a finitely generated commutative algebra over a field of characteristic zero. We prove that every finitely generated Lie subalgebra $L\subseteq\operatorname{…

cs.LG2025

Control Disturbance Rejection in Neural ODEs

Erkan Bayram, Mohamed-Ali Belabbas, Tamer Başar

In this paper, we propose an iterative training algorithm for Neural ODEs that provides models resilient to control (parameter) disturbances. The method builds on our earlier work…

cs.LG2025

Geometric Foundations of Tuning without Forgetting in Neural ODEs

Erkan Bayram, Mohamed-Ali Belabbas, Tamer Başar

In our earlier work, we introduced the principle of Tuning without Forgetting (TwF) for sequential training of neural ODEs, where training samples are added iteratively and paramet…

math.OC2025

Interpretable Gradient Descent for Kalman Gain

M. A. Belabbas, A. Olshevsky

We derive a decomposition for the gradient of the innovation loss with respect to the filter gain in a linear time-invariant system, decomposing as a product of an observability Gr…

math.OC2025

On the invariance of super-linearization under polynomial automorphisms

Anmol Harshana, Mohamed-Ali Belabbas

We prove that the super-linearizability of polynomial systems is preserved by all currently known classes of polynomial automorphisms of . We then establish connections betwe…

math.OC2025

Constructing Stochastic Matrices for Weighted Averaging in Gossip Networks

Erkan Bayram, Mohamed-Ali Belabbas

The convergence of the gossip process has been extensively studied; however, algorithms that generate a set of stochastic matrices, the infinite product of which converges to a ran…