Andrew Bennett

Andrew Bennett

PhD Student

Cornell University

Biography

I am a fifth year PhD student at Cornell University in the Computer Science department, supervised by Nathan Kallus. My current research focus is at the intersection of causal inference, machine learning, and econometrics, with particular interest in causal inference under unmeasured confounding, reinforcement learning, and efficiently solving high-dimensional conditional moment problems. Previously, during my Masters at the University of Melbourne, I conducted research in Natural Language Processing and Computational Linguistics.

Interests

  • Causal Inference
  • Machine Learning
  • Reinforcement Learning
  • Econometrics

Education

  • Master of Science in Computer Science, 2016

    The University of Melbourne

  • Bachelor of Science, 2013

    The University of Melbourne

Publications

Quickly discover relevant content by filtering publications.
(2022). Provable Safe Reinforcement Learning with Binary Feedback. arXiv Preprint.

PDF

(2022). The Variational Method of Moments. Major revision in JRSS:B.

PDF

(2022). Future-Dependent Value-Based Off-Policy Evaluation in POMDPs. arXiv Preprint.

PDF

(2021). Have you tried Neural Topic Models? Comparative Analysis of Neural and Non-Neural Topic Models with Application to COVID-19 Twitter Data. The 3rd Workshop on Data Science for Social Good (DSSG-21).

PDF

(2021). Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders. International Conference on Artificial Intelligence and Statistics (AISTATS).

PDF

(2020). Efficient Policy Learning from Surrogate-Loss Classification Reductions. International Conference on Machine Learning (ICML).

PDF

(2019). Deep Generalized Method of Moments for Instrumental Variable Analysis. Advances in Neural Information Processing Systems (NeurIPS).

PDF

(2019). Policy Evaluation with Latent Confounders via Optimal Balance. Advances in Neural Information Processing Systems (NeurIPS).

PDF

(2018). Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction. Conference on Empirical Methods in Natural Language Processing (EMNLP).

PDF

(2018). Preferred answer selection in stack overflow: Better text representations... and metadata, metadata, metadata. The 4th Workshop on Noisy User-generated Text (W-NUT), at EMNLP.

PDF

(2018). Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning. Robotics: Science and Systems (RSS).

PDF

(2018). Detecting Misflagged Duplicate Questions in Community Question-Answering Archives. The AAAI Conference on Web and Social Media (ICWSM).

PDF

(2018). CHALET: Cornell House Agent Learning Environment. Technical Report.

PDF

(2016). LexSemTM: A Semantic Dataset Based on All-words Unsupervised Sense Distribution Learning. The Annual Meeting of the Association for Computational Linguistics (ACL).

PDF

(2016). Unsupervised All-words Sense Distribution Learning. Masters Thesis.

PDF

Contact