I am a postdoc at the Institute of Science and Technology (IST) Austria in the Henzinger Group. In fall 2022 I will be joining the Department of Computer Science and Engineering at the Pennsylvania State University as a Hartz Family Career Development Assistant Professor. Before joining IST, I completed my PhD from the University of Texas at Austin advised by Prof. Swarat Chaudhuri. My research lies at the intersection of machine learning and formal methods, with a focus on building intelligent systems that are reliable, transparent, and secure. This work builds connections between the symbolic reasoning and inductive learning paradigms of artificial intelligence.

Research Overview

My research combines ideas from formal methods and machine learning to efficiently build models that are reliable, transparent, and secure. This means that such a system can be expected to learn desirable behaviors with limited data, while provably maintaining some essential correctness invariant and generating models whose decisions can be understood by humans. I believe that we can achieve these goals via Neurosymbolic learning.

[Read More] Current machine learning models are dominated by Deep Neural Networks, because they are capable of leveraging gradient-based algorithms to optimize a specific objective. However, neural models are considered “black-boxes” and are often considered untrustworthy due to the following drawbacks:
  1. Hard to interpret: this makes these models hard to audit and debug.
  2. Hard to formally verify: due to the lack of abstractions in neural models they are often too large to verify for desirable behavior using automated reasoning tools.
  3. Unreliable: neural models have notoriously high levels of variability, to the extent that the random initialization of the weights can determine whether the learner finds a useful model.
  4. Lack of domain awareness: neural models lack the ability to bias the learner with commonsense knowledge about the task or environment.
My research focuses on addressing these four drawbacks simultaneously, and provides a promising path to discovering new algorithmic techniques leading to Trustworthy Artificial Intelligence.





Standalone Instructor

  • Math 105: University Mathematics.
    Introduction to logic, combinatorics, and probability. Core requirement for BS degree.

  • Math 111: College Algebra.
    Foundational course in algebra, functions, and mathematical modeling. Calculus preparation course, prerequisite for higher-level math courses.

  • Math 112: Elementary Functions.
    Focus on mathematical induction and trigonometric functions. Precalculus designed for math, biology, physiology, and CS majors.

Teaching Assistant

  • COMP 539: Software Engineering Methodology.
    Project based graduate course on software engineering.

  • COMP 503: Reasoning About Software.
    Graduate course on formal methods and automated reasoning.

  • COMP 310: Advanced Object-Oriented Programming and Design.
    Senior undergraduate course on OOP.

  • Math 243: Introduction to Probability and Statistics.
    Undergraduate course on statistical reasoning.

  • M01: Introduction to Mathematical Thinking.
    First course on abstract mathematics.