publications

Publications and preprints in reverse chronological order.

2026

  1. TMLR
    Unrealized Expectations: Comparing AI Methods vs Classical Algorithms for Maximum Independent Set
    Yikai Wu, Haoyu Zhao, and Sanjeev Arora
    Transactions on Machine Learning Research, Apr 2026
    arXiv HTML

2025

  1. NeurIPS
    AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
    Ori Press, Brandon Amos, Haoyu Zhao, Yikai Wu, Samuel Ainsworth, and 19 more authors
    Advances in Neural Information Processing SystemsDatasets and Benchmarks Track , 2025
    DOI arXiv HTML

2022

  1. COLT
    Private Matrix Approximation and Geometry of Unitary Orbits
    Oren Mangoubi, Yikai Wu, Satyen Kale, Abhradeep Thakurta, and Nisheeth K Vishnoi
    In Proceedings of Thirty Fifth Conference on Learning Theory, 2022
    arXiv HTML

2021

  1. VLDB
    Budget Sharing for Multi-Analyst Differential Privacy
    David Pujol, Yikai Wu, Brandon Fain, and Ashwin Machanavajjhala
    Proceedings of the VLDB Endowment, 2021
    DOI arXiv HTML

2020

  1. Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks
    Yikai Wu, Xingyu Zhu, Chenwei Wu, Annie Wang, and Rong Ge
    arXiv preprint arXiv:2010.04261, 2020
    arXiv

2019

  1. TPDP
    Answering Summation Queries for Numerical Attributes under Differential Privacy
    Yikai Wu, David Pujol, Ios Kotsogiannis, and Ashwin Machanavajjhala
    arXiv preprint arXiv:1908.10268Poster at the Workshop on Theory and Practice of Differential Privacy (TPDP), 2019 , 2019
    arXiv