About me
I am a final year PhD student at the Institute of Science and Technology Austria (ISTA) where I am supervised by Krishnendu Chatterjee and Petr Novotný. Prior to joining ISTA, I obtained my undergraduate and master degrees in mathematics at the University of Cambridge, where I was a student at the lovely Gonville & Caius College. You may find my CV here.
Research Interests
My research focuses on developing formal methods and automated reasoning techniques for verifying properties of software and AI enabled systems. My research lies at the intersection of formal methods, programming languages, artificial intelligence and machine learning, and I work in the broad areas of formal software verification and AI safety.
The central theme of my work are formal methods and automated reasoning techniques for stochastic systems. Stochastic systems provide a model for reasoning about uncertainty that can arise in software and AI enabled systems in various forms, e.g. through randomisation, interactions with uncertain environments or learning from data. My goal is to lay theoretical and algorithmic foundations towards enabling formal methods and automated reasoning to tackle stochastic systems with the same level of success with which formal methods can handle non-probabilistic software systems. Additionally, I am interested in designing formal methods that can enhance performance of stochastic control methods and reinforcement learning algorithms under safety constraints.
More concretely, my current research interests include:
- Probabilistic Verification
- Static Program Analysis
- Probabilistic Programming
- Learning-based Control
- Neural Network Verification
- Safe Reinforcement Learning
- (Stochastic) Games on Graphs
News
April 2023. Our work MDPs as Distribution Transformers: Affine Invariant Synthesis for Safety Objectives has been accepted at CAV 2023. Thanks and congrats to my coauthors!
February 2023. Our work On Lexicographic Proof Rules for Probabilistic Termination has been accepted in Formal Aspects of Computing. Thanks and congrats to my coauthors!
January 2023. I will be attending AAAI 2023 in Washington, D.C., for the whole duration of the conference. Reach out if you will be around and would like to connect!
January 2023. Artifact Evaluation Committee member for CAV 2023.
November 2022. Very excited to share that 3 of our papers have been accepted at AAAI 2023. Thanks and congrats to my coauthors!
- Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees
- Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks
- Bidding Graph Games with Partially-Observable Budgets
- Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees