World's Best Scientists 2026 revealed!
Award Badge
Rising Stars
2025

D-Index & Metrics

Rising Stars

D-Index
36
Citations
5447
World Ranking
793
National Ranking
131

Computer Science

D-Index
33
Citations
5032
World Ranking
12625
National Ranking
5112

Research.com Recognitions

  • 2025 - Research.com Rising Stars Award

Overview

Zhao Song is a researcher affiliated with Adobe Systems in the United States. They have contributed extensively to the field of Computer Science, with a focus on several subfields including Artificial Intelligence, Computational Theory and Mathematics, Computer Vision and Pattern Recognition, Numerical Analysis, and Computational Mechanics.

Their research spans a broad range of advanced topics within computer science, including:

  • Stochastic Gradient Optimization Techniques
  • Complexity and Algorithms in Graphs
  • Sparse and Compressive Sensing Techniques
  • Machine Learning and Algorithms
  • Advanced Optimization Algorithms Research
  • Privacy-Preserving Technologies in Data
  • Quantum Computing Algorithms and Architecture

Zhao Song has been published in a variety of academic venues, with a frequent presence in preprint archives and journals such as:

  • arXiv (Cornell University)
  • Leibniz-Zentrum für Informatik (Schloss Dagstuhl)
  • SIAM Journal on Computing
  • Journal of the ACM
  • Journal of Cleaner Production

Selected publications by Zhao Song include:

  • "China's population spatialization based on three machine learning models", 2020, Journal of Cleaner Production
  • "Solving Linear Programs in the Current Matrix Multiplication Time", 2021, Journal of the ACM
  • "Faster Dynamic Matrix Inverse for Faster LPs", 2020, arXiv (Cornell University)
  • "An improved quantum-inspired algorithm for linear regression", 2022, Quantum
  • "A study on water quality parameters estimation for urban rivers based on ground hyperspectral remote sensing technology", 2022, Environmental Science and Pollution Research

Throughout their career, Zhao Song has collaborated with several frequent coauthors, highlighting ongoing research partnerships. These include:

  • Zhenmei Shi
  • Yingyu Liang
  • Ruizhe Zhang
  • Zhizhou Sha
  • Yin Tat Lee

Best Publications

  • A Convergence Theory for Deep Learning via Over-Parameterization

    Zeyuan Allen-Zhu;Yuanzhi Li;Zhao Song

  • A Convergence Theory for Deep Learning via Over-Parameterization

    Zeyuan Allen-Zhu;Yuanzhi Li;Zhao Song

  • Towards Fast Computation of Certified Robustness for ReLU Networks

    Tsui-Wei Weng;Huan Zhang;Hongge Chen;Zhao Song

  • Solving Linear Programs in the Current Matrix Multiplication Time

    Michael B. Cohen;Yin Tat Lee;Zhao Song

  • Recovery Guarantees for One-hidden-layer Neural Networks

    Kai Zhong;Zhao Song;Prateek Jain;Peter L. Bartlett

  • Solving linear programs in the current matrix multiplication time

    Michael B. Cohen;Yin Tat Lee;Zhao Song

  • Towards Fast Computation of Certified Robustness for ReLU Networks

    Tsui-Wei Weng;Huan Zhang;Hongge Chen;Zhao Song

  • Recovery Guarantees for One-hidden-layer Neural Networks

    Kai Zhong;Zhao Song;Prateek Jain;Peter L. Bartlett

  • On the Convergence Rate of Training Recurrent Neural Networks

    Zeyuan Allen-Zhu;Yuanzhi Li;Zhao Song

  • Low rank approximation with entrywise l1-norm error

    Zhao Song;David P. Woodruff;Peilin Zhong

  • The Limitations of Adversarial Training and the Blind-Spot Attack

    Huan Zhang;Hongge Chen;Zhao Song;Duane S. Boning

  • Parallel Graph Connectivity in Log Diameter Rounds

    Alexandr Andoni;Zhao Song;Clifford Stein;Zhengyu Wang

  • Evaluating Gradient Inversion Attacks and Defenses in Federated Learning

    Yangsibo Huang;Samyak Gupta;Zhao Song;Kai Li

  • Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound.

    Zhao Song;Xin Yang

  • Relative error tensor low rank approximation

    Zhao Song;David P. Woodruff;Peilin Zhong

  • Faster Dynamic Matrix Inverse for Faster LPs.

    Shunhua Jiang;Zhao Song;Omri Weinstein;Hengjie Zhang

  • Solving tall dense linear programs in nearly linear time

    Jan van den Brand;Yin Tat Lee;Aaron Sidford;Zhao Song

  • Bipartite Matching in Nearly-linear Time on Moderately Dense Graphs

    Jan van den Brand;Yin-Tat Lee;Danupon Nanongkai;Richard Peng

  • A Faster Interior Point Method for Semidefinite Programming

    Haotian Jiang;Tarun Kathuria;Yin Tat Lee;Swati Padmanabhan

  • Minimum cost flows, MDPs, and ℓ1-regression in nearly linear time for dense instances

    Jan van den Brand;Yin Tat Lee;Yang P. Liu;Thatchaphol Saranurak

  • Weighted low rank approximations with provable guarantees

    Ilya Razenshteyn;Zhao Song;David P. Woodruff

  • Learning Non-overlapping Convolutional Neural Networks with Multiple Kernels

    Kai Zhong;Zhao Song;Inderjit S. Dhillon

  • InstaHide: Instance-hiding Schemes for Private Distributed Learning

    Yangsibo Huang;Zhao Song;Kai Li;Sanjeev Arora

  • Parallel Graph Connectivity in Log Diameter Rounds

    Alexandr Andoni;Clifford Stein;Zhao Song;Zhengyu Wang

  • Batch Codes Through Dense Graphs Without Short Cycles

    Ankit Singh Rawat;Zhao Song;Alexandros G. Dimakis;Anna Gal

  • Meta-learning for mixed linear regression

    Weihao Kong;Raghav Somani;Zhao Song;Sham Kakade

Frequent Co-Authors

David P. Woodruff
David P. Woodruff Carnegie Mellon University
Yin Tat Lee
Yin Tat Lee Microsoft (United States)
Inderjit S. Dhillon
Inderjit S. Dhillon Google (United States)
Sanjeev Arora
Sanjeev Arora Princeton University
Kai Li
Kai Li Princeton University
Aaron Sidford
Aaron Sidford Stanford University
Simon S. Du
Simon S. Du University of Washington
Huan Zhang
Huan Zhang University of California, Los Angeles
Yuanzhi Li
Yuanzhi Li Carnegie Mellon University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online education in Computer Science opens doors to a variety of academic routes and professional opportunities. When choosing a degree, it’s important to investigate the majors that align with your career goals and the current job market demand.

For those seeking to advance their qualifications quickly, some candidates search for the easiest masters degree to get online, making it more accessible for busy professionals or career changers.

If your ambitions include a doctorate, affordability is often a top concern. Fortunately, there are options for the cheapest doctorate degree online, helping reduce financial barriers to the highest levels of education.

Speed to completion is another consideration for many learners. If you’re aiming for a doctoral-level education in education specifically, you may want to explore the fastest edd program online to accelerate your progress and get back into the workforce quickly.

Best Scientists Citing Zhao Song

Trending Scientists

Recently Published Articles