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

D-Index & Metrics

Rising Stars

D-Index
39
Citations
7443
World Ranking
685
National Ranking
104

Engineering and Technology

D-Index
34
Citations
6237
World Ranking
9154
National Ranking
2567

Research.com Recognitions

  • 2025 - Research.com Rising Stars Award

Overview

Simon S. Du is affiliated with the University of Washington in the United States. Their research contributions are primarily situated in the field of Computer Science, with substantial work in subfields such as Artificial Intelligence, Management Science and Operations Research, Computer Networks and Communications, Computational Mechanics, and Electrical and Electronic Engineering.

Their research spans several key topics, including:

  • Reinforcement Learning in Robotics
  • Advanced Bandit Algorithms Research
  • Machine Learning and Algorithms
  • Adversarial Robustness in Machine Learning
  • Domain Adaptation and Few-Shot Learning
  • Sparse and Compressive Sensing Techniques
  • Optimization and Search Problems

Simon S. Du has published extensively, with frequent contributions to venues such as:

  • arXiv (Cornell University) - 108 publications
  • Journal of the ACM - 2 publications
  • Mathematical Programming - 1 publication
  • Information Fusion - 1 publication
  • SSRN Electronic Journal - 1 publication

Some recent papers authored or co-authored by Simon S. Du include:

  • "Understanding the acceleration phenomenon via high-resolution differential equations," 2021, Mathematical Programming
  • "How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks," 2020, arXiv (Cornell University)
  • "Few-Shot Learning via Learning the Representation, Provably," 2020, arXiv (Cornell University)
  • "On Reward-Free Reinforcement Learning with Linear Function Approximation," 2020, arXiv (Cornell University)
  • "Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon," 2020, arXiv (Cornell University)

The scientist has collaborated frequently with several co-authors, including:

  • Jason D. Lee
  • Kevin Jamieson
  • Qiwen Cui
  • Maryam Fazel
  • Ruosong Wang

Best Publications

  • Gradient Descent Provably Optimizes Over-parameterized Neural Networks

    Simon S. Du;Xiyu Zhai;Barnabas Poczos;Aarti Singh

  • Gradient descent finds global minima of deep neural networks

    Simon S. Du;Jason D. Lee;Haochuan Li;Liwei Wang

  • Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks

    Sanjeev Arora;Simon S. Du;Wei Hu;Zhiyuan Li

  • On Exact Computation with an Infinitely Wide Neural Net

    Sanjeev Arora;Simon S. Du;Wei Hu;Zhiyuan Li

  • Understanding the acceleration phenomenon via high-resolution differential equations

    Bin Shi;Simon S. Du;Michael I. Jordan;Weijie J. Su

  • On the Power of Over-parametrization in Neural Networks with Quadratic Activation

    Simon S. Du;Jason D. Lee

  • Gradient Descent Can Take Exponential Time to Escape Saddle Points

    Simon S. Du;Chi Jin;Jason D. Lee;Michael I. Jordan

  • Gradient Descent Learns One-hidden-layer CNN: Don’t be Afraid of Spurious Local Minima

    Simon S. Du;Jason D. Lee;Yuandong Tian;Barnabas Poczos

  • How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks

    Keyulu Xu;Mozhi Zhang;Jingling Li;Simon Shaolei Du

  • Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

    Sanjeev Arora;Simon S. Du;Zhiyuan Li;Ruslan Salakhutdinov

  • Enhanced Convolutional Neural Tangent Kernels

    Zhiyuan Li;Ruosong Wang;Dingli Yu;Simon S. Du

  • Stochastic Variance Reduction Methods for Policy Evaluation

    Simon S. Du;Jianshu Chen;Lihong Li;Lin Xiao

  • What Can Neural Networks Reason About

    Keyulu Xu;Jingling Li;Mozhi Zhang;Simon S. Du

  • Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced

    Simon S. Du;Wei Hu;Jason D. Lee

  • Few-Shot Learning via Learning the Representation, Provably

    Simon Shaolei Du;Wei Hu;Sham M. Kakade;Jason D. Lee

  • Gradient Descent Can Take Exponential Time to Escape Saddle Points

    Simon S. Du;Chi Jin;Jason D. Lee;Michael I. Jordan

  • Provably efficient RL with Rich Observations via Latent State Decoding

    Simon S. Du;Akshay Krishnamurthy;Nan Jiang;Alekh Agarwal

  • Computationally Efficient Robust Sparse Estimation in High Dimensions

    Sivaraman Balakrishnan;Simon S. Du;Jerry Li;Aarti Singh

  • Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

    Simon S. Du;Kangcheng Hou;Russ R. Salakhutdinov;Barnabas Poczos

  • Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity

    Simon S. Du;Wei Hu

  • Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning

    Simon S. Du;Sham M. Kakade;Ruosong Wang;Lin F. Yang

  • On Reward-Free Reinforcement Learning with Linear Function Approximation

    Ruosong Wang;Simon S. Du;Lin F. Yang;Ruslan Salakhutdinov

Frequent Co-Authors

Jason D. Lee
Jason D. Lee Princeton University
Aarti Singh
Aarti Singh Carnegie Mellon University
Barnabás Póczos
Barnabás Póczos Carnegie Mellon University
Sanjeev Arora
Sanjeev Arora Princeton University
Ruslan Salakhutdinov
Ruslan Salakhutdinov Carnegie Mellon University
Sham M. Kakade
Sham M. Kakade Harvard University
Yuandong Tian
Yuandong Tian Facebook (United States)
Michael I. Jordan
Michael I. Jordan University of California, Berkeley
Jiajun Wu
Jiajun Wu Stanford University
Zhao Song
Zhao Song Adobe Systems (United States)

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

Engineering and Technology students can benefit from exploring related online degrees to broaden their career prospects. For those interested in law and regulations within the tech industry, aba accredited paralegal programs offer valuable legal training relevant to intellectual property and patent work.

Leadership positions in technical companies often require advanced skills. Earning a 1 year online master's in human resources can prepare engineers and technologists to manage teams and recruit top talent.

Communication skills are vital for project management and client relations. An online masters in communications helps professionals bridge gaps between technical and non-technical stakeholders.

For those with entrepreneurial goals, pursuing an online mba entrepreneurship provides essential knowledge for launching startups or leading innovative projects in tech-driven industries.

These online pathways complement an Engineering and Technology background, allowing graduates to stand out in today's diverse and competitive job market.

Best Scientists Citing Simon S. Du

Trending Scientists