Manuscripts

  • How Much Data is Sufficient to Learn High-Performing Algorithms?
    with Maria-Florina Balcan, Dan DeBlasio, Travis Dick, Carl Kingsford, and Tuomas Sandholm
    [paper] [slides]

  • Private Optimization Without Constraint Violations
    with Andrés Muñoz, Umar Syed, and Sergei Vassilvitskii
    Preliminary versions in the Privacy in Machine Learning Workshop (PriML) at the Conference on Neural Information Processing Systems (NeurIPS) 2019 and Theory and Practice of Differential Privacy (TPDP) 2020
    [paper] [poster]

Conference publications

  • Refined Bounds for Algorithm Configuration: The Knife-edge of Dual Class Approximability
    with Maria-Florina Balcan and Tuomas Sandholm
    International Conference on Machine Learning (ICML) 2020
    [paper] [slides] [video]

  • Learning to Optimize Computational Resources: Frugal Training with Generalization Guarantees
    with Maria-Florina Balcan and Tuomas Sandholm
    AAAI Conference on Artificial Intelligence 2020
    [paper] [poster]

  • Estimating Approximate Incentive Compatibility
    with Maria-Florina Balcan and Tuomas Sandholm
    ACM Conference on Economics and Computation (EC) 2019
    🏆 Exemplary Artificial Intelligence Track Paper Award (EC 2019)
    🏆 Best Presentation by a Student or Postdoctoral Researcher (EC 2019)
    [paper] [slides] [video] [poster]

  • Learning to Prune: Speeding up Repeated Computations
    with Daniel Alabi, Adam Tauman Kalai, Katrina Ligett, Cameron Musco, and Christos Tzamos
    Conference on Learning Theory (COLT) 2019
    [paper] [slides] [video] [poster]

  • Algorithmic Greenlining: An Approach to Increase Diversity
    with Christian Borgs, Jennifer Chayes, Nika Haghtalab, and Adam Tauman Kalai
    AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES) 2019
    [paper] [slides] [poster]

  • Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization
    with Maria-Florina Balcan and Travis Dick
    IEEE Symposium on Foundations of Computer Science (FOCS) 2018
    [paper] [slides] [poster]

  • Learning to Branch
    with Maria-Florina Balcan, Travis Dick, and Tuomas Sandholm
    International Conference on Machine Learning (ICML) 2018
    [paper] [slides] [video]

  • A General Theory of Sample Complexity for Multi-Item Profit Maximization
    with Maria-Florina Balcan and Tuomas Sandholm
    ACM Conference on Economics and Computation (EC) 2018
    [paper] [slides]

  • Synchronization Strings: Channel Simulations and Interactive Coding for Insertions and Deletions
    with Bernhard Haeupler and Amirbehshad Shahrasbi
    International Colloquium on Automata, Languages and Programming (ICALP) 2018
    [paper]

  • Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems
    with Maria-Florina Balcan, Vaishnavh Nagarajan, and Colin White
    Conference on Learning Theory (COLT) 2017
    [paper] [slides]

  • Sample Complexity of Automated Mechanism Design
    with Maria-Florina Balcan and Tuomas Sandholm
    Conference on Neural Information Processing Systems (NeurIPS) 2016
    [paper] [slides] [video]

  • Learning Combinatorial Functions from Pairwise Comparisons
    with Maria-Florina Balcan and Colin White
    Conference on Learning Theory (COLT) 2016
    [paper]