I am an AI research scientist at GE Healthcare. My research largely focuses on (deep) probabilistic machine learning methods for healthcare applications, specifically for sequential and multi-modal settings. Prior to joining GE Healthcare, I was a statistics PhD student at the University of California, Irvine under the advisement of Dr. Padhraic Smyth and Dr. Stephan Mandt.
While there, my research primarily pertained to investigating efficient methods of evaluating various probabilistic queries of black-box sequential models (e.g., large language models, temporal point processes, etc.) that extend beyond immediate next value prediction.
I was fortunate to have the opportunity to research these topics and others during my PhD due to receiving a NSF Graduate Research Fellowship in 2020. Prior to starting my PhD program, I received a Bachelor’s of Science degree in software engineering with a minor in data science at the California Polytechnic State University, San Luis Obispo under the advisement of Dr. Dennis Sun. I have also conducted machine learning research as an intern at Apple, Microsoft Research, and NVIDIA.
Papers
On the Efficient Marginalization of Probabilistic Sequence Models
Alex Boyd
PhD Dissertation, 2024
Understanding Pathologies of Deep Heteroskedastic Regression
Eliot Wong-Toi, Alex Boyd, Vincent Fortuin, Stephan Mandt
Preprint (currently under review), 2024
Probabilistic Modeling for Sequences of Sets in Continuous-Time
Yuxin Chang, Alex Boyd, Padhraic Smyth
(To Appear) International Conference on Artificial Intelligence and Statistics (AIStats), 2024 [Oral Presentation]
Bayesian Online Learning for Consensus Prediction
Samuel Showalter*, Alex Boyd*, Padhraic Smyth, Mark Steyvers
(To Appear) International Conference on Artificial Intelligence and Statistics (AIStats), 2024
salmon: A Symbolic Linear Regression Package for Python
Alex Boyd, Dennis Sun
(To Appear) Journal of Statistical Software, 2024
Inference for Mark-Censored Temporal Point Processes
Alex Boyd, Yuxin Chang, Stephan Mandt, Padhraic Smyth
Conference on Uncertainty in Artificial Intelligence (UAI), 2023 [Spotlight Presentation]
Probabilistic Querying of Continuous-Time Event Sequences
Alex Boyd, Yuxin Chang, Stephan Mandt, Padhraic Smyth
International Conference on Artificial Intelligence and Statistics (AIStats), 2023
Predictive Querying for Autoregressive Neural Sequence Models
Alex Boyd*, Samuel Showalter*, Stephan Mandt, Padhraic Smyth
Neural Information Processing Systems (NeurIPS). 2022 [Oral Presentation]
Structured Stochastic Gradient MCMC
Antonios Alexos*, Alex Boyd*, Stephan Mandt
International Conference on Machine Learning (ICML), 2022
Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning
Aodong Li, Alex Boyd, Padhraic Smyth, Stephan Mandt
Neural Information Processing Systems (NeurIPS), 2021
Dynamic Survival Analysis for EHR Data with Personalized Parametric Distributions
Preston Putzel, Hyungrok Do, Alex Boyd, Hua Zhong, Padhraic Smyth
Machine Learning for Healthcare Conference (MLHC), 2021
Large Scale Multi-Actor Generative Dialog Modeling
Alex Boyd*, Raul Puri*, Mohammad Shoeybi, Mostofa Patwary, Bryan Catanzaro
Association for Computational Linguistics (ACL). 2020
User-Dependent Neural Sequence Models for Continuous-Time Event Data
Alex Boyd, Robert Bamler, Stephan Mandt, Padhraic Smyth
Neural Information Processing Systems (NeurIPS), 2020
(*) denotes shared first-authorship