works on

From the 1 of 20 linked papers with an AI index.

collaborators

20 papers

eess.SY2026

Wasserstein Stability of Contracting Flows: Effective Rates, Euler Self-Correction, and Noise Tightening

Ali Baheri

The paper derives tighter Wasserstein‑based stability bounds for nonlinear contracting systems, analyzes the self‑correcting behavior of Euler discretization errors, and shows that…

eess.SY2026

Flow-Corrected Thompson Sampling for Non-Stationary Contextual Bandits

AmirHossein Naghdi, Ali Baheri

We study non-stationary linear contextual bandits where the reward model drifts over time, rendering classical contextual bandit algorithms brittle because historical data becomes…

cs.LG2026

Metriplectic Conditional Flow Matching for Dissipative Dynamics

Ali Baheri, Lars Lindemann

Metriplectic conditional flow matching (MCFM) learns dissipative dynamics without violating first principles. Neural surrogates often inject energy and destabilize long-horizon rol…

cs.LG2026

Geometry-Aware Uncertainty Quantification via Conformal Prediction on Manifolds

Marzieh Amiri Shahbazi, Ali Baheri

Conformal prediction gives finite-sample coverage guarantees for regression, but most standard constructions are designed for Euclidean output spaces. When the response lies on a R…

cs.AI2026

Can We Formally Verify Neural PDE Surrogates? SMT Compilation of Small Fourier Neural Operators

Ali Baheri, Ignacio Laguna Peralta

Fourier Neural Operators (FNOs) can greatly accelerate PDE simulation, but they are often used without formal guarantees that they preserve basic physical structure. We show that,…

eess.SY2026

Geometry-Aware Decentralized Sinkhorn for Wasserstein Barycenters

Ali Baheri, Alireza Vahid

Distributed systems require fusing heterogeneous local probability distributions into a global summary over sparse and unreliable communication networks. Traditional consensus algo…