Aubrey Barnard

---

I do machine learning research, focusing on medical applications of causal discovery in electronic health records databases. My research interests include causal inference, probabilistic graphical models, event history analysis / time series, multi-relational rule learning, and databases.

In 2019, I earned my PhD in Computer Sciences from the University of Wisconsin, advised by David Page (who has moved to Duke). My dissertation was on discovering the adverse effects of medications, through learning the structure of Bayesian network causal models, and through analyzing observational studies with machine learning for hypothesizing drug effects. This research produced a new method for Bayesian network structure learning, and a novel causal discovery machine learning approach based on analyzing before–after studies with temporal inverse probability weighting.

While I mostly work with Python (e.g., scikit-learn, NumPy / SciPy, matplotlib, PyTorch), I have been writing all my numerical code in Julia. It is as easy to use as Python—it is interactive, high-level, expressive, multi-paradigm, dynamically-typed—but it runs at machine speed and has linear algebra and concurrency built in. I encourage you to check Julia out!

I ran the UW–Madison ML and AI Reading Group for 5 semesters.

---

Research Interests

• Causality
• Probabilistic graphical models
• Event sequences / time series (patient histories in electronic health records can be modeled as irregular, sparse, and noisy sequences of events)
• Multi-Relational rule learning (inductive logic programming)
• Databases

Other Interests

• Open source software
• Software design and development
• Programming languages
• Linux
• Go (the game, but the language is cool, too)

Current Projects

• Effects of common drugs in electronic health records on the survival of patients
• Learning the structure of Markov and Bayesian networks via convex optimization
• Faster optimization for log-linear models

Selected Papers

• Temporal Inverse Probability Weighting for Discovering Adverse Drug Events Especially in Generic Drugs
  Aubrey Barnard, David Page, Peggy Peissig, Meng Hu
  In submission

• Causal Discovery of Adverse Drug Events in Observational Data
  Aubrey Barnard
  PhD Dissertation, Computer Sciences, University of Wisconsin–Madison, 2019

• Causal Structure Learning via Temporal Markov Networks
  Aubrey Barnard, David Page
  Probabilistic Graphical Models 9, 2018

• Identifying Adverse Drug Events by Relational Learning
  David Page, Vítor Santos Costa, Sriraam Natarajan, Aubrey Barnard, Peggy Peissig, Michael Caldwell
  AAAI 26, 2012

Google Scholar Profile