World's Best Scientists 2026 revealed!

D-Index & Metrics

Engineering and Technology

D-Index
53
Citations
10971
World Ranking
3392
National Ranking
1001

Jason D. Lee publication distribution in Engineering and Technology in 2026

The chart shows the distribution of publications by all Research.com ranked scientists in the field of Engineering and Technology in 2026. The highlighted bar marks where Jason D. Lee sits on this spectrum.

38–47 publications: 20 scientists 48–57 publications: 35 scientists 58–67 publications: 96 scientists 68–77 publications: 134 scientists 78–87 publications: 190 scientists 88–97 publications: 259 scientists 98–107 publications: 283 scientists 108–117 publications: 369 scientists 118–127 publications: 341 scientists 128–137 publications: 386 scientists 138–147 publications: 372 scientists 148–157 publications: 457 scientists 158–167 publications: 415 scientists 168–177 publications: 407 scientists 178–187 publications: 421 scientists 188–197 publications: 378 scientists 198–207 publications: 403 scientists 208–217 publications: 317 scientists 218–227 publications: 346 scientists 228–237 publications: 321 scientists 238–247 publications: 260 scientists 248–257 publications: 280 scientists 258–267 publications: 240 scientists 268–277 publications: 214 scientists 278–287 publications: 242 scientists 288–297 publications: 203 scientists 298–307 publications: 166 scientists 308–317 publications: 154 scientists 318–327 publications: 175 scientists 328–337 publications: 159 scientists 338–347 publications: 99 scientists 348–357 publications: 131 scientists 358–367 publications: 106 scientists 368–377 publications: 117 scientists 378–387 publications: 97 scientists 388–397 publications: 108 scientists 398–407 publications: 82 scientists 408–417 publications: 71 scientists 418–427 publications: 64 scientists 428–437 publications: 55 scientists 438–447 publications: 54 scientists 448–457 publications: 59 scientists 458–467 publications: 47 scientists 468–477 publications: 40 scientists 478–487 publications: 30 scientists 488–497 publications: 29 scientists 498–507 publications: 38 scientists 508–517 publications: 40 scientists 518–527 publications: 32 scientists 528–537 publications: 23 scientists 538–547 publications: 28 scientists 548–557 publications: 23 scientists 558–567 publications: 19 scientists 568–577 publications: 16 scientists 578–587 publications: 17 scientists 588–597 publications: 18 scientists 598–607 publications: 22 scientists 608–617 publications: 15 scientists 618–627 publications: 9 scientists 628–637 publications: 11 scientists 638–647 publications: 21 scientists 648–657 publications: 12 scientists 658–667 publications: 9 scientists 668–677 publications: 11 scientists 678–687 publications: 9 scientists 688–697 publications: 6 scientists 698–707 publications: 14 scientists 708–717 publications: 7 scientists 718–727 publications: 8 scientists 728–737 publications: 10 scientists 738–747 publications: 9 scientists 748–757 publications: 5 scientists 758–767 publications: 5 scientists 768–777 publications: 11 scientists 778–787 publications: 7 scientists 788–797 publications: 2 scientists 798–803 publications: 4 scientists 804+ publications: 100 scientists
38 publications 804+

This scientist: 154 publications — 29th percentile

29% of scientists in this discipline score the same or lower.

The last bar groups every scientist with 804 publications or more.

Jason D. Lee D-index placement in Engineering and Technology in 2026

The chart shows the D-index (discipline H-index) distribution of Engineering and Technology scientists ranked by Research.com in 2026. The highlighted bar marks where Jason D. Lee sits on this spectrum.

30 D-Index: 59 scientists 31 D-Index: 114 scientists 32 D-Index: 128 scientists 33 D-Index: 189 scientists 34 D-Index: 200 scientists 35 D-Index: 262 scientists 36 D-Index: 311 scientists 37 D-Index: 312 scientists 38 D-Index: 350 scientists 39 D-Index: 385 scientists 40 D-Index: 349 scientists 41 D-Index: 362 scientists 42 D-Index: 425 scientists 43 D-Index: 380 scientists 44 D-Index: 310 scientists 45 D-Index: 341 scientists 46 D-Index: 301 scientists 47 D-Index: 306 scientists 48 D-Index: 271 scientists 49 D-Index: 246 scientists 50 D-Index: 210 scientists 51 D-Index: 253 scientists 52 D-Index: 213 scientists 53 D-Index: 221 scientists 54 D-Index: 195 scientists 55 D-Index: 186 scientists 56 D-Index: 170 scientists 57 D-Index: 167 scientists 58 D-Index: 166 scientists 59 D-Index: 144 scientists 60 D-Index: 152 scientists 61 D-Index: 141 scientists 62 D-Index: 138 scientists 63 D-Index: 131 scientists 64 D-Index: 118 scientists 65 D-Index: 114 scientists 66 D-Index: 119 scientists 67 D-Index: 94 scientists 68 D-Index: 87 scientists 69 D-Index: 77 scientists 70 D-Index: 89 scientists 71 D-Index: 69 scientists 72 D-Index: 54 scientists 73 D-Index: 46 scientists 74 D-Index: 55 scientists 75 D-Index: 54 scientists 76 D-Index: 49 scientists 77 D-Index: 53 scientists 78 D-Index: 46 scientists 79 D-Index: 28 scientists 80 D-Index: 39 scientists 81 D-Index: 36 scientists 82 D-Index: 24 scientists 83 D-Index: 26 scientists 84 D-Index: 36 scientists 85 D-Index: 18 scientists 86 D-Index: 24 scientists 87 D-Index: 19 scientists 88 D-Index: 26 scientists 89 D-Index: 27 scientists 90 D-Index: 23 scientists 91 D-Index: 15 scientists 92 D-Index: 12 scientists 93 D-Index: 9 scientists 94 D-Index: 15 scientists 95 D-Index: 10 scientists 96 D-Index: 13 scientists 97 D-Index: 13 scientists 98 D-Index: 9 scientists 99 D-Index: 7 scientists 100 D-Index: 7 scientists 101 D-Index: 8 scientists 102 D-Index: 7 scientists 103 D-Index: 7 scientists 104 D-Index: 9 scientists 105 D-Index: 6 scientists 106 D-Index: 9 scientists 107+ D-Index: 99 scientists
30 D-Index 107+

This scientist: 53 D-Index — 66th percentile

66% of scientists in this discipline score the same or lower.

The last bar groups every scientist with 107 D-Index or more.

Overview

Jason D. Lee is affiliated with Princeton University in the United States and has contributed extensively to research in computer science, particularly focusing on artificial intelligence and related subfields. Their work spans multiple domains such as management science and operations research, statistics and probability, statistical and nonlinear physics, and computer networks and communications.

The scientist's publication record includes a significant number of papers in prominent venues. The frequent publication outlets include:

  • arXiv (Cornell University)
  • Journal of the ACM
  • The Annals of Statistics
  • Journal of the American Statistical Association
  • SIAM Journal on Optimization

Their research covers a broad spectrum of topics related to machine learning and optimization techniques. Main research topics include:

  • Reinforcement Learning in Robotics
  • Advanced Bandit Algorithms Research
  • Stochastic Gradient Optimization Techniques
  • Machine Learning and Algorithms
  • Domain Adaptation and Few-Shot Learning
  • Sparse and Compressive Sensing Techniques
  • Model Reduction and Neural Networks

Jason D. Lee frequently collaborates with several researchers, including:

  • Simon S. Du
  • Wenhao Zhan
  • Eshaan Nichani
  • Baihe Huang
  • Qi Lei

Some recent papers authored or co-authored by Jason D. Lee include:

  • Predicting What You Already Know Helps: Provable Self-Supervised Learning (2020, arXiv, Cornell University)
  • Fine-Tuning Language Models with Just Forward Passes (2023, arXiv, Cornell University)
  • Statistical inference for model parameters in stochastic gradient descent (2020, The Annals of Statistics)
  • Few-Shot Learning via Learning the Representation, Provably (2020, arXiv, Cornell University)
  • Distributed Estimation for Principal Component Analysis: An Enlarged Eigenspace Analysis (2021, Journal of the American Statistical Association)

Their research emphasizes theoretical and applied aspects of learning algorithms, including work on model parameters estimation, representation learning, and distributed estimation techniques. This aligns with their significant publication output and contributions within artificial intelligence and operations research fields.

Best Publications

  • Gradient descent finds global minima of deep neural networks

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

  • Matrix completion and low-rank SVD via fast alternating least squares

    Trevor Hastie;Rahul Mazumder;Jason D. Lee;Reza Zadeh

  • Gradient descent only converges to minimizers

    Jason D. Lee;Max Simchowitz;Michael I. Jordan;Benjamin Recht

  • Matrix Completion has No Spurious Local Minimum

    Rong Ge;Jason D. Lee;Tengyu Ma

  • Communication-Efficient Distributed Statistical Inference

    Michael I. Jordan;Jason D. Lee;Yun Yang

  • Ubiquitination-dependent mechanisms regulate synaptic growth and function

    Aaron DiAntonio;Ali P. Haghighi;Scott L. Portman;Jason D. Lee

  • Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks

    Mahdi Soltanolkotabi;Adel Javanmard;Jason D. Lee

  • PROXIMAL NEWTON-TYPE METHODS FOR MINIMIZING COMPOSITE FUNCTIONS

    Jason D. Lee;Yuekai Sun;Michael A. Saunders

  • A kernelized stein discrepancy for goodness-of-fit tests

    Qiang Liu;Jason D. Lee;Michael Jordan

  • Implicit Bias of Gradient Descent on Linear Convolutional Networks

    Suriya Gunasekar;Jason D. Lee;Daniel Soudry;Nathan Srebro

  • Characterizing Implicit Bias in Terms of Optimization Geometry

    Suriya Gunasekar;Jason D. Lee;Daniel Soudry;Nathan Srebro

  • Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes

    Alekh Agarwal;Sham M. Kakade;Jason D. Lee;Gaurav Mahajan

  • On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift

    Alekh Agarwal;Sham M. Kakade;Jason D. Lee;Gaurav Mahajan

  • Gradient Descent Converges to Minimizers.

    Jason D. Lee;Max Simchowitz;Michael I. Jordan;Benjamin Recht

  • 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

  • Stochastic Subgradient Method Converges on Tame Functions

    Damek Davis;Dmitriy Drusvyatskiy;Sham M. Kakade;Jason D. Lee

  • Solving a class of non-convex min-max games using iterative first order methods

    Maher Nouiehed;Maziar Sanjabi;Tianjian Huang;Jason D. Lee

  • Practical Large-Scale Optimization for Max-norm Regularization

    Jason D Lee;Ben Recht;Nathan Srebro;Joel Tropp

  • First-order methods almost always avoid strict saddle points

    Jason D. Lee;Ioannis Panageas;Georgios Piliouras;Max Simchowitz

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

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

  • Learning one-hidden-layer neural networks with landscape design

    Rong Ge;Jason D. Lee;Tengyu Ma

Frequent Co-Authors

Simon S. Du
Simon S. Du University of Washington
Michael I. Jordan
Michael I. Jordan University of California, Berkeley
Jonathan Taylor
Jonathan Taylor Stanford University
Nathan Srebro
Nathan Srebro Toyota Technological Institute at Chicago
Tengyu Ma
Tengyu Ma Stanford University
Daniel Soudry
Daniel Soudry Technion – Israel Institute of Technology
Sham M. Kakade
Sham M. Kakade Harvard University
Meisam Razaviyayn
Meisam Razaviyayn University of Southern California
Qiang Liu
Qiang Liu Chinese Academy of Sciences
Michael A. Saunders
Michael A. Saunders Stanford 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:

Best Scientists Citing Jason D. Lee

Trending Scientists