Morris Yau Ph.D Candidate MIT Computer Science

I am Morris a Ph.D Candidate at MIT in EECS in the group of Prof. Ankur Moitra. My research is broadly in the area of algorithms, with a focus on those that are valuable for AI. Computational and statistical efficiency are vital aspects of any learning system, and therefore these considerations shape the major themes of my research. Towards these ends, I am currently focused on studying neural networks as computational artifacts. My interests include deep learning theory, computation of game theoretic solution concepts, the design of algorithms and statistical estimators for reinforcement learning/control, and the good old fight of probing the fundamental limitations of classification, clustering, and approximation.

In the before times I received my masters in computer science from UC Berkeley under the wonderful supervision of Prof. Prasad Raghavendra who is also my Ph.D advisor. And before that I was an undergraduate at Harvard University where I had the great fortune to work with Prof. Madhu Sudan on aspects of algebraic complexity.

Manuscripts

Author order alphabetical, *indicates first authorship

  • Are Graph Neural Networks Optimal Approximation Algorithms?
    Authors: Morris Yau*, Eric Lu, Nikolaos Karalias, Jessica Xu, Stefanie Jegelka
    Venue: Neurips 2023 workshop Mathematics of Modern Machine Learning (M3L)
    Arxiv Link: https://arxiv.org/abs/2310.00526

Publications

  • Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems
    Authors: Ainesh Bakshi, Allen Liu, Ankur Moitra, Morris Yau
    Venue: 40th ICML
  • A New Approach To Learning Linear Dynamical Systems
    Authors: Ainesh Bakshi, Allen Liu, Ankur Moitra, Morris Yau
    Venue: 55th Annual ACM Symposium on Theory of Computing (STOC 2023)
    Arxiv Link: https://arxiv.org/abs/2301.09519
  • Kalman Filtering with Adversarial Corruptions
    Authors: Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau
    Venue: 54th Annual ACM Symposium on Theory of Computing (STOC 2022)
    Arxiv Link: https://arxiv.org/pdf/2111.06395.pdf
  • Online and Distribution Free Robustness: Regression and Contextual Bandits with Huber Contamination
    Authors: Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau
    Venue: Proceedings of the 62nd Annual IEEE Symposium on Foundations of Computer Science (FOCS 2021)
    Arxiv Link: https://arxiv.org/abs/2010.04157
  • Classification under Misspecfication: Halfspaces, Generalized Linear Models, and Connections to Evolvability
    Authors: Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau
    Venue: Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Spotlight
    Arxiv Link: https://arxiv.org/abs/2006.04787
  • List Decodable Mean Estimation in Nearly Linear Time
    Authors: Yeshwanth Cherapanamjeri, Sidhanth Mohanty, Morris Yau
    Venue: Proceedings of the 61st Annual IEEE Symposium on Foundations of Computer Science (FOCS 2020)
    Arxiv Link: https://arxiv.org/abs/2005.09796
  • List Decodable Subspace Recovery
    Authors: Prasad Raghavendra and Morris Yau
    Venue: The 33rd Annual Conference on Learning Theory (COLT 2020)
    Arxiv Link: https://arxiv.org/abs/2002.03004
  • List Decodable Learning via Sum of Squares
    Authors: Prasad Raghavendra and Morris Yau
    Venue: Proceedings of the Thirty-First Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2020)
    Arxiv Link: https://arxiv.org/abs/1905.04660