63 citations · 81 across the 42 of their papers we have counts for
44 papers
Controller-Agnostic Runtime Safety Certificates for Tool-Using AI Agents via Data-Driven Robust Reachability
Ali Baheri, Peng Wei
Software agents built on large language models act by issuing tool calls, some of which cannot be undone. To control theory the model is an opaque feedback controller, replaced eve…
Flow-Corrected Thompson Sampling for Non-Stationary Contextual Bandits
Ali Baheri, AmirHossein Naghdi
We study non-stationary linear contextual bandits where the reward model drifts over time, rendering classical contextual bandit algorithms brittle because historical data becomes…
Wasserstein Stability of Contracting Flows: Effective Rates, Euler Self-Correction, and Noise Tightening
Ali Baheri
Contraction theory guaranties exponential convergence between trajectories of a stable nonlinear system. When initial conditions are uncertain and represented as probability distri…
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,…
Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry
Tyler Alvarez, Ali Baheri
Large language models hallucinate during multi-step reasoning, but most existing detectors operate at the trace level: they assign one confidence score to a full output, fail to lo…
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…
Adaptive Conformal Prediction via Bayesian Uncertainty Weighting for Hierarchical Healthcare Data
Marzieh Amiri Shahbazi, Ali Baheri, Nasibeh Azadeh-Fard
Clinical decision-making demands uncertainty quantification that provides both distribution-free coverage guarantees and risk-adaptive precision, requirements that existing methods…
Can Optimal Transport Improve Federated Inverse Reinforcement Learning?
David Millard, Ali Baheri
In robotics and multi-agent systems, fleets of autonomous agents often operate in subtly different environments while pursuing a common high-level objective. Directly pooling their…
Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets
Shriram Karpoora Sundara Pandian, Ali Baheri
Offline reinforcement learning (RL) enables policy optimization from fixed datasets, making it suitable for safety-critical applications where online exploration is infeasible. How…
Split Conformal Prediction in the Function Space with Neural Operators
David Millard, Lars Lindemann, Ali Baheri
Uncertainty quantification for neural operators remains an open problem in the infinite-dimensional setting due to the lack of finite-sample coverage guarantees over functional out…
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…
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…
Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning
Ali Baheri
Cooperative multi-agent reinforcement learning (MARL) demands principled mechanisms to align heterogeneous policies while preserving the capacity for specialized behavior. We intro…
Implicit Constraint-Aware Off-Policy Correction for Offline Reinforcement Learning
Ali Baheri
Offline reinforcement learning promises policy improvement from logged interaction data alone, yet state-of-the-art algorithms remain vulnerable to value over-estimation and to vio…
DEF: Diffusion-augmented Ensemble Forecasting
David Millard, Arielle Carr, Stéphane Gaudreault +1
We present DEF (\textbf{\ul{D}}iffusion-augmented \textbf{\ul{E}}nsemble \textbf{\ul{F}}orecasting), a novel approach for generating initial condition perturbations. Modern approac…
Wasserstein Barycenter Soft Actor-Critic
Zahra Shahrooei, Ali Baheri
Deep off-policy actor-critic algorithms have emerged as the leading framework for reinforcement learning in continuous control domains. However, most of these algorithms suffer fro…
PEARL: Preconditioner Enhancement through Actor-critic Reinforcement Learning
David Millard, Arielle Carr, Stéphane Gaudreault +1
We present PEARL (Preconditioner Enhancement through Actor-critic Reinforcement Learning), a novel approach to learning matrix preconditioners. Existing preconditioners such as Jac…
Multi-Scale Conformal Prediction: A Theoretical Framework with Coverage Guarantees
Ali Baheri, Marzieh Amiri Shahbazi
We propose a multi-scale extension of conformal prediction, an approach that constructs prediction sets with finite-sample coverage guarantees under minimal statistical assumptions…
Optimal Transport-Guided Safety in Temporal Difference Reinforcement Learning
Zahra Shahrooei, Ali Baheri
The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering safety. In contrast, safe rein…
SMTL: A Stratified Logic for Expressive Multi-Level Temporal Specifications
Ali Baheri, Peng Wei
We present Stratified Metric Temporal Logic (SMTL), a novel formalism for specifying and verifying properties of complex cyber-physical systems that exhibit behaviors across multip…
Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning
Ali Baheri, Zahra Shahrooei, Chirayu Salgarkar
We present Wasserstein Adaptive Value Estimation for Actor-Critic (WAVE), an approach to enhance stability in deep reinforcement learning through adaptive Wasserstein regularizatio…
Hierarchical Upper Confidence Bounds for Constrained Online Learning
Ali Baheri
The multi-armed bandit (MAB) problem is a foundational framework in sequential decision-making under uncertainty, extensively studied for its applications in areas such as clinical…
Optimizing Falsification for Learning-Based Control Systems: A Multi-Fidelity Bayesian Approach
Zahra Shahrooei, Mykel J. Kochenderfer, Ali Baheri
Testing controllers in safety-critical systems is vital for ensuring their safety and preventing failures. In this paper, we address the falsification problem within learning-based…
Optimal Transport-Assisted Risk-Sensitive Q-Learning
Zahra Shahrooei, Ali Baheri
The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance without considering risk or safety. In contrast, safe reinforc…