2026 Jason D. Lee: Engineering and Technology Researcher – H-Index, Publications & Awards

D-Index & Metrics

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Engineering and Technology	53	3392	3246	1001	914	154	10971

Discipline name

D-Index

World Ranking

Current World Ranking

National Ranking

Current National Ranking

Publications

Citations

Engineering and Technology

3392

3246

1001

914

154

10971

Engineering and Technology

D-Index

Citations

10971

World Ranking

3392

National Ranking

1001

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

692
Citations
Matrix completion and low-rank SVD via fast alternating least squares

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

558
Citations
Gradient descent only converges to minimizers

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

549
Citations
Matrix Completion has No Spurious Local Minimum

Rong Ge;Jason D. Lee;Tengyu Ma

534
Citations
Communication-Efficient Distributed Statistical Inference

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

502
Citations
Ubiquitination-dependent mechanisms regulate synaptic growth and function

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

455
Citations
Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks

Mahdi Soltanolkotabi;Adel Javanmard;Jason D. Lee

386
Citations
PROXIMAL NEWTON-TYPE METHODS FOR MINIMIZING COMPOSITE FUNCTIONS

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

328
Citations
A kernelized stein discrepancy for goodness-of-fit tests

Qiang Liu;Jason D. Lee;Michael Jordan

312
Citations
Implicit Bias of Gradient Descent on Linear Convolutional Networks

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

244
Citations
Characterizing Implicit Bias in Terms of Optimization Geometry

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

242
Citations
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes

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

233
Citations
On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift

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

212
Citations
Gradient Descent Converges to Minimizers.

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

202
Citations
On the Power of Over-parametrization in Neural Networks with Quadratic Activation

Simon S. Du;Jason D. Lee

201
Citations
Gradient Descent Can Take Exponential Time to Escape Saddle Points

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

198
Citations
Stochastic Subgradient Method Converges on Tame Functions

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

189
Citations
Solving a class of non-convex min-max games using iterative first order methods

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

185
Citations
Practical Large-Scale Optimization for Max-norm Regularization

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

182
Citations
First-order methods almost always avoid strict saddle points

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

175
Citations
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced

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

110
Citations
Learning one-hidden-layer neural networks with landscape design

Rong Ge;Jason D. Lee;Tengyu Ma

78
Citations