Most are also listed on Google Scholar.
* Denotes co-first author.

Conference and Journal Publications

Benchmarking of Machine Learning Ocean Subgrid Parameterizations in an Idealized Model
Andrew Slavin Ross, Ziwei Li, Pavel Perezhogin, Carlos Fernandez-Granda, and Laure Zanna
Journal of Advances in Modeling Earth Systems, 2022 [pdf] [link] [code] [data]
Tackling Climate Change with Machine Learning
David Rolnick, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques, Anna Waldman-Brown, Alexandra Luccioni, Tegan Maharaj, Evan D. Sherwin, S. Karthik Mukkavilli, Konrad P. Kording, Carla Gomes, Andrew Y. Ng, Demis Hassabis, John C. Platt, Felix Creutzig, Jennifer Chayes, and Yoshua Bengio
ACM Computing Surveys, 2022 [pdf] [link] [preprint]
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
Andrew Slavin Ross and Finale Doshi-Velez
Evaluating the Interpretability of Generative Models by Interactive Reconstruction
Andrew Slavin Ross, Nina Chen, Elisa Zhao Hang, Elena L. Glassman, and Finale Doshi-Velez
Assessment of a Prediction Model for Antidepressant Treatment Stability Using Supervised Topic Models
Michael C. Hughes, Melanie F. Pradier, Andrew Slavin Ross, Thomas H. McCoy Jr., Roy H. Perlis, and Finale Doshi-Velez
JAMA Psychiatry, 2020 [pdf] [link]
Ensembles of Locally Independent Prediction Models
Andrew Slavin Ross, Weiwei Pan, Leo Anthony Celi, and Finale Doshi-Velez
Design Continuums and the Path Towards Self-Designing Key-Value Stores that Know and Learn
Stratos Idreos, Niv Dayan, Wilson Qin, Mali Akmanalp, Sophie Hilgard, Andrew Slavin Ross, James Lennon, Varun Jain, Harshita Gupta, David Li, and Zichen Zhu
Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning
Xuefeng Peng, Yi Ding, David Wihl, Omer Gottesman, Matthieu Komorowski, Li-wei H. Lehman, Andrew Slavin Ross, Aldo Faisal, and Finale Doshi-Velez
AMIA, 2018 [pdf] [link]
Human-in-the-Loop Interpretability Prior
Isaac Lage, Andrew Slavin Ross, Been Kim, Samuel J. Gershman, and Finale Doshi-Velez
NeurIPS, 2018 [pdf] [link]
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
Andrew Slavin Ross and Finale Doshi-Velez
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
Andrew Slavin Ross, Michael C. Hughes, and Finale Doshi-Velez
IJCAI, 2017 [pdf] [link] [code] [slides]
Hydrodynamic Irreversibility in Particle Suspensions with Non-Uniform Strain
Jeffrey S. Guasto, Andrew Slavin Ross, and J. P. Gollub
Physical Review E, 2010 [pdf] [link]

Theses

Right for the Right Reasons: Training Neural Networks to be Interpretable, Robust, and Consistent with Expert Knowledge
Andrew Slavin Ross
PhD Thesis, Harvard University, 2021 [pdf] [slides] 🏆 Outstanding Dissertation Award
Training Machine Learning Models by Regularizing their Explanations
Andrew Slavin Ross
Master's Thesis, Harvard University, 2018 [pdf] [link] [slides]
The Compression and Concentration of Classical and Quantum Information
Andrew Slavin Ross and Peter Love
Senior Thesis, Haverford College, 2011 [pdf]

Workshop Papers

Behavioral Experiments for Gathering Labeled Animal Vocalization Data
Andrew Slavin Ross* and Su Jin Kim*
Intl. Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots (VIHAR), 2021 [link] [slides]
Controlled Direct Effect Priors for Bayesian Neural Networks
Jianzhun Du*, Andrew Slavin Ross*, Yonadav Shavit*, and Finale Doshi-Velez
NeurIPS Workshop on Bayesian Deep Learning, 2019 [pdf] [link] [slides]
Refactoring Machine Learning
Andrew Slavin Ross and Jessica Zosa Forde
NeurIPS Workshop on Critiquing and Correcting Trends in Machine Learning, 2018 [pdf]
Learning Qualitatively Diverse and Interpretable Rules for Classification
Andrew Slavin Ross*, Weiwei Pan*, and Finale Doshi-Velez
ICML Workshop on Human Interpretability in Machine Learning, 2018 [pdf] [link] [code] [slides]
The Neural LASSO: Local Linear Sparsity for Interpretable Explanations
Andrew Slavin Ross*, Isaac Lage*, and Finale Doshi-Velez
NeurIPS Workshop on on Transparent and Interpretable Machine Learning in Safety Critical Environments, 2017 [pdf]