Publication

2025

• All-Purpose Mean Estimation over \(\mathbb{R}\): Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance.
  Jasper C.H. Lee, Walter McKelvie, Maoyuan Song, Paul Valiant.
  ICML 2025.
  Selected for spotlight poster.

• Untrusted Predictions and Mean Estimation: Machine-Learning Primitives from Data-Dependent Perspectives.
  Maoyuan Song.
  PhD Thesis, Purdue University. [link]

• Communication With Perfect Feedback for Bit Flips and Erasures.
  Elena Grigorescu, Shreya Nasa, Maoyuan Song.
  ISIT 2025.

• Learning-Augmented Algorithms for Online Concave Packing and Convex Covering Problems.
  Elena Grigorescu, Young-San Lin, Maoyuan Song.
  AISTATS 2025. [arXiv]
  Merge of:

  • Learning-Augmented Algorithms for Online Covering Programs with Convex Objectives.
  • A Simple Learning-Augmented Algorithm for Online Packing with Concave Objectives.
    [arXiv]

2023

• Optimality in Mean Estimation: Beyond Worst-Case, Beyond Sub-Gaussian, and Beyond \(1 + \alpha\) Moments.
  Trung Dang, Jasper C.H. Lee, Maoyuan Song, Paul Valiant.
  NeurIPS 2023. [arXiv]

2022

• Learning-Augmented Algorithms for Online Linear and Semidefinite Programming.
  Elena Grigorescu, Young-San Lin, Sandeep Silwal, Maoyuan Song, Samson Zhou.
  NeurIPS 2022. [arXiv]
  Selected for spotlight presentation.

2020

• Linear Time Addition of Fibonacci Encodings.
  Maoyuan Song.
  Master’s Thesis, Carnegie Mellon University. [link]