Publications

See also my Google Scholar page.
* Denotes co-first author

Papers

• Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization
  Bingqing Chen*, Priya L. Donti*, Kyri Baker, J. Zico Kolter, Mario Berges
  🏆 Best paper runner-up at the ACM International Conference on Future Energy Systems (ACM e-Energy) 2021
  [paper]   [code]

• DC3: A learning method for optimization with hard constraints
  Priya L. Donti*, David Rolnick*, J. Zico Kolter
  International Conference on Learning Representations (ICLR) 2021
  [paper]   [poster]   [code]

• Enforcing robust control guarantees within neural network policies
  Priya L. Donti, Melrose Roderick, Mahyar Fazlyab, J. Zico Kolter
  International Conference on Learning Representations (ICLR) 2021
  [paper]   [poster]   [code]

• Tackling Climate Change with Machine Learning (preprint)
  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, Yoshua Bengio
  ^†Co-editor of full paper, and sole author of Electricity Systems section.
  [paper]   [press coverage]

• SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver
  Po-Wei Wang, Priya L. Donti, Bryan Wilder, and J. Zico Kolter
  🏆 Best paper honorable mention at the International Conference on Machine Learning (ICML) 2019
  [paper]   [poster]   [slides]   [code]

• Matrix Completion for Low-Observability Voltage Estimation
  Priya L. Donti, Yajing Liu, Andreas J. Schmitt, Andrey Bernstein, Rui Yang, and Yingchen Zhang
  IEEE Transactions on Smart Grid (2019)
  [paper]

• How Much Are We Saving after All? Characterizing the Effects of Commonly Varying Assumptions on Emissions and Damage Estimates in PJM
  Priya L. Donti, J. Zico Kolter, and Inês Lima Azevedo
  Environmental Science & Technology (2019)
  [paper]   [code]

• Task-based End-to-End Model Learning in Stochastic Optimization
  Priya L. Donti, Brandon Amos, and J. Zico Kolter
  Neural Information Processing Systems (NeurIPS) 2017
  [paper]   [poster]   [video]   [code]

Selected Workshop Papers, Reports, and Posters

• Artificial Intelligence and Climate Change: Opportunities, considerations, and policy levers to align AI with climate change goals
  Lynn H. Kaack, Priya L. Donti, Emma Strubell, David Rolnick
  Heinrich Böll Foundation E-Paper (2020)
  [paper]   [video]

• An adversarially robust approach to security-constrained optimal power flow
  Neeraj Vijay Bedmutha, Priya L. Donti, J. Zico Kolter
  Machine Learning for Engineering Modeling, Simulation, and Design workshop at NeurIPS 2020
  [paper]   [poster]   [video]

• Forecasting Marginal Emissions Factors in PJM
  Amy Wang, Priya L. Donti
  Tackling Climate Change with Machine Learning workshop at NeurIPS 2020
  [proposal]   [video]   [slides]

• A Call for Universities to Develop Requirements for Community Engagement in AI Research
  Emily Black, Joshua Williams, Michael A. Madaio, Priya L. Donti
  Position paper at the CHI 2020 Fair & Responsible AI Workshop
  [paper]

• Inverse Optimal Power Flow: Assessing the Vulnerability of Power Grid Data
  Priya L. Donti, Inês Lima Azevedo, and J. Zico Kolter
  🏆 Highlighted paper at the AI for Social Good workshop at NeurIPS 2018
  🏆 Best poster at the Power and Energy Conference at Illinois (PECI) 2019
  [paper]   [poster]

• Predicting the Quality of User Experiences to Improve Productivity and Wellness
  Priya L. Donti, Jacob Rosenbloom, Alex Gruver, and James C. Boerkoel Jr.
  Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)
  [poster abstract]

• Exploring Active and Passive Team-Based Coordination
  Priya L. Donti and James C. Boerkoel Jr.
  Artificial Intelligence for Human-Robot Interaction at the 2014 AAAI Fall Symposium
  [abstract]