Teddy Koker

Teddy Koker

I am currently a machine learning researcher at MIT Lincoln Laboratory, where I am a member of the Artificial Intelligence Technology group.

Previously, I have worked at Lightning AI and Harvard Medical School.

Email / CV / Github / Google Scholar / Twitter

Research

I am broadly interested in machine learning and its applications to the sciences and medicine. My most recent work focuses on machine learning within the field of material science, as well as methods for domain adaptation and interpretability of time-series models.


Higher-Order Equivariant Neural Networks for Charge Density Prediction in Materials
Teddy Koker, Keegan Quigley, Eric Taw, Kevin Tibbetts, Lin Li.
In Review. Also at NeurIPS AI for Science Workshop, 2023.
arXiv / Code


Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency
Owen Queen, Thomas Hartvigsen, Teddy Koker, Huan He, Theodoros Tsiligkaridis, Marinka Zitnik
NeurIPS, 2023 (spotlight).
arXiv / Code / Website


Domain Adaptation for Time Series Under Feature and Label Shifts
Huan He, Owen Queen, Teddy Koker, Consuelo Cuevas, Theodoros Tsiligkaridis, Marinka Zitnik.
International Conference on Machine Learning (ICML), 2023.
arXiv / Code / Website


Graph Contrastive Learning for Materials
Teddy Koker, Keegan Quigley, Will Spaeth, Nathan C. Frey, and Lin Li.
NeurIPS AI for Accelerated Materials Design Workshop, 2022.
arXiv


AAVAE: Augmentation-Augmented Variational Autoencoders.
William Falcon, Ananya Harsh Jha, Teddy Koker, and Kyunghyun Cho.
Preprint.
arXiv / Code


TorchMetrics: Measuring Reproducibility in PyTorch
N. Detlefsen, J. Borovec, J. Schock, A. Jha, T. Koker, L. Liello, D. Stancl, C. Quan, M. Grechkin, W. Falcon.
The Journal of Open Source Software, 2022.
Publication / Code


U-Noise: Learnable Noise Masks for Interpretable Image Segmentation.
T. Koker, F. Mireshghallah, T. Titcombe, and G. Kaissis.
International Conference on Image Processing (ICIP), 2021.
Publication / arXiv / Code


On Identification and Retrieval of Near-Duplicate Biological Images: A New Dataset and Protocol.
T. Koker*, S.S. Chintapalli*, S. Wang, B.A. Talbot, D. Wainstock, M. Cicconet, M.C. Walsh.
International Conference on Pattern Recognition (ICPR), 2020.
Publication / PDF / Code


Cryptocurrency Trading Using Machine Learning.
Teddy Koker and Dimitrios Koutmos.
Journal of Risk and Financial Management, 2020.
Publication