Machine Learning with Optimization Layers Involved
Differentiable optimization
Can we inject more reasoning in the machine learning models?
Can we achieve end-to-end learning when optimization layers are involved?
Decision-focused learning integrates optimization in the loop of machine learning to align with specific tasks. We are interested in how to make different decision-making problems differentiable and efficiently back-propagatable.
New era of differentiable optimization: bilevel optimization and predict-then-optimize
Fully First-Order Methods for Linearly Constrained Bilevel Optimization
Guy Kornowski*, Swati Padmanabhan*, Kai Wang*, Zhe Zhang*, Suvrit Sra (NeurIPS 2024)
Differentiable everything (sequential problems, Nash equilibrium)
Restless Multi-Armed Bandits for Maternal and Child Health: Results from Decision-Focused Learning
Shresth Verma, Aditya Mate, Kai Wang, Neha Madhiwalla, Aparna Hegde, Aparna Taneja, Milind Tambe (AAMAS 2023)Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health
Kai Wang*, Shresth Verma*, Aditya Mate, Sanket Shah, Aparna Taneja, Neha Madhiwalla, Aparna Hegde, Milind Tambe (AAAI 2023)Coordinating Followers to Reach Better Equilibria: End-to-End Gradient Descent for Stackelberg Games
Kai Wang, Lily Xu, Andrew Perrault, Michael K. Reiter, and Milind Tambe (AAAI 2022)Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning
Kai Wang, Sanket Shah, Haipeng Chen, Andrew Perrault, Finale Doshi-Velez, and Milind Tambe (NeurIPS 2021 spotlight presentation)
Decision-focused learning algorithms
What is the Right Notion of Distance between Predict-then-Optimize Tasks?
Paula Rodriguez-Diaz, Lingkai Kong, Kai Wang, David Alvarez-Melis, Milind Tambe (in submission)Characterizing and Improving the Robustness of Predict-Then-Optimize Frameworks
Sonja Johnson-Yu, Jessica Finocchiaro, Arunesh Sinha, Kai Wang, Yevgeniy Vorobeychik, Aparna Taneja, Milind Tambe (GameSec 2023)Decision-Focused Learning without Decision-Making: Learning Locally Optimized Decision Losses
Sanket Shah, Kai Wang, Bryan Wilder, Andrew Perrault, Milind Tambe (NeurIPS 2022)Automatically Learning Compact Quality-aware Surrogates for Optimization Problems
Kai Wang, Bryan Wilder, Andrew Perrault, and Milind Tambe (NeurIPS 2020 spotlight presentation)Scalable Game-Focused Learning of Adversary Models:Data-to-Decisions in Network Security Games
Kai Wang, Andrew Perrault, Aditya Mate, and Milind Tambe (AAMAS 2020)