28 citations · 53 across the 6 of their papers we have counts for
6 papers
Into the Unknown: Active Monitoring of Neural Networks
Anna Lukina, Christian Schilling, Thomas A. Henzinger
Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where…
MurTree: Optimal Classification Trees via Dynamic Programming and Search
Emir Demirović, Anna Lukina, Emmanuel Hebrard +5
Decision tree learning is a widely used approach in machine learning, favoured in applications that require concise and interpretable models. Heuristic methods are traditionally us…
Formal Methods with a Touch of Magic
Parand Alizadeh Alamdari, Guy Avni, Thomas A. Henzinger +1
Machine learning and formal methods have complimentary benefits and drawbacks. In this work, we address the controller-design problem with a combination of techniques from both fie…
Adaptive Neighborhood Resizing for Stochastic Reachability in Multi-Agent Systems
Anna Lukina, Ashish Tiwari, Scott A. Smolka +1
We present DAMPC, a distributed, adaptive-horizon and adaptive-neighborhood algorithm for solving the stochastic reachability problem in multi-agent systems, in particular flocking…
Attacking the V: On the Resiliency of Adaptive-Horizon MPC
Scott A. Smolka, Ashish Tiwari, Lukas Esterle +3
We introduce the concept of a V-formation game between a controller and an attacker, where controller's goal is to maneuver the plant (a simple model of flocking dynamics) into a V…
ARES: Adaptive Receding-Horizon Synthesis of Optimal Plans
Anna Lukina, Lukas Esterle, Christian Hirsch +5
We introduce ARES, an efficient approximation algorithm for generating optimal plans (action sequences) that take an initial state of a Markov Decision Process (MDP) to a state who…