2026 Rong Ge: Computer Science Researcher – H-Index, Publications & Awards

Overview

Rong Ge is affiliated with Duke University in the United States, with a body of research spanning multiple areas within computer science and engineering. Their work primarily focuses on artificial intelligence, computational mechanics, and statistical methods, with significant contributions to multiple subfields and topics related to machine learning and optimization.

Their main fields of study include:

Computer Science
Engineering

The subfields of study Rong Ge has contributed to are:

Artificial Intelligence
Computational Mechanics
Statistics and Probability
Civil and Structural Engineering
Biomedical Engineering

Main topics covered in their research include:

Sparse and Compressive Sensing Techniques
Stochastic Gradient Optimization Techniques
Statistical Methods and Inference
Markov Chains and Monte Carlo Methods
Optimization and Search Problems
Machine Learning and Algorithms
Machine Learning and Data Classification

Rong Ge's published papers reflect detailed investigations in these fields, including the following recent works:

"On Nonconvex Optimization for Machine Learning," 2021, Journal of the ACM
"Hydro-refining of coal-petroleum co-processing oil for potential clean jet fuels," 2022, Fuel
"Customizing ML Predictions for Online Algorithms," 2022, arXiv (Cornell University)
"Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks," 2020, arXiv (Cornell University)
"A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network," 2021, arXiv (Cornell University)

The frequent publication venues where Rong Ge has shared research include:

arXiv (Cornell University)
Journal of the ACM
Fuel
Mathematical Programming
SSRN Electronic Journal

They have collaborated frequently with a number of researchers including:

Muthu Chidambaram
Yu Cheng
Ilias Diakonikolas
Chi Jin
Keerti Anand

Best Publications

Tensor decompositions for learning latent variable models

Animashree Anandkumar;Rong Ge;Daniel Hsu;Sham M. Kakade

1200
Citations
Escaping from saddle points: Online stochastic gradient for tensor decomposition

Rong Ge;Furong Huang;Chi Jin;Yang Yuan

975
Citations
How to escape saddle points efficiently

Chi Jin;Rong Ge;Praneeth Netrapalli;Sham M. Kakade

623
Citations
Generalization and Equilibrium in Generative Adversarial Nets (GANs)

Sanjeev Arora;Rong Ge;Yingyu Liang;Tengyu Ma

575
Citations
Matrix Completion has No Spurious Local Minimum

Rong Ge;Jason D. Lee;Tengyu Ma

534
Citations
Learning Topic Models -- Going beyond SVD

Sanjeev Arora;Rong Ge;Ankur Moitra

492
Citations
A Practical Algorithm for Topic Modeling with Provable Guarantees

Sanjeev Arora;Rong Ge;Yonatan Halpern;David Mimno

474
Citations
Stronger generalization bounds for deep nets via a compression approach

Sanjeev Arora;Rong Ge;Behnam Neyshabur;Yi Zhang

427
Citations
Provable Bounds for Learning Some Deep Representations

Sanjeev Arora;Aditya Bhaskara;Rong Ge;Tengyu Ma

398
Citations
Computing a nonnegative matrix factorization -- provably

Sanjeev Arora;Rong Ge;Ravindran Kannan;Ankur Moitra

386
Citations
No spurious local minima in nonconvex low rank problems: a unified geometric analysis

Rong Ge;Chi Jin;Yi Zheng

350
Citations
Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator.

Maryam Fazel;Rong Ge;Sham M. Kakade;Mehran Mesbahi

337
Citations
New algorithms for learning in presence of errors

Sanjeev Arora;Rong Ge

328
Citations
A Tensor Spectral Approach to Learning Mixed Membership Community Models

Animashree Anandkumar;Rong Ge;Daniel J. Hsu;Sham M. Kakade

270
Citations
New Algorithms for Learning Incoherent and Overcomplete Dictionaries

Sanjeev Arora;Rong Ge;Ankur Moitra

206
Citations
A tensor approach to learning mixed membership community models

Animashree Anandkumar;Rong Ge;Daniel Hsu;Sham M. Kakade

192
Citations
Simple, Efficient, and Neural Algorithms for Sparse Coding

Sanjeev Arora;Rong Ge;Tengyu Ma;Ankur Moitra

178
Citations
Guaranteed Non-Orthogonal Tensor Decomposition via Alternating Rank-$1$ Updates

Animashree Anandkumar;Rong Ge;Majid Janzamin

163
Citations
Computational complexity and information asymmetry in financial products

Sanjeev Arora;Boaz Barak;Markus Brunnermeier;Rong Ge

134
Citations
Learning one-hidden-layer neural networks with landscape design

Rong Ge;Jason D. Lee;Tengyu Ma

78
Citations

Frequent Co-Authors

Sanjeev Arora Princeton University

Sham M. Kakade Harvard University

Tengyu Ma Stanford University

Ankur Moitra MIT

Praneeth Netrapalli Google (United States)

Michael I. Jordan University of California, Berkeley

Anima Anandkumar Nvidia (United Kingdom)

Daniel Hsu Columbia University

Jason D. Lee Princeton University

Aaron Sidford Stanford University

External Links

Personal website of Rong Ge Google Scholar page

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

Related Online Degrees & Career Pathways

If you’re exploring options beyond a traditional Computer Science degree, several flexible online programs can kick-start or advance your tech career. For those seeking quick entry into the workforce, consider easy licenses and certifications to get. These programs can often be completed in months, offering practical skills and strong earning potential in areas like IT support, cybersecurity, or data analytics.

Interested in a more advanced qualification? Look into shortest master degree programs in technology or business. These accelerated graduate degrees can help you upskill quickly, usually in a year or less, making them ideal for career changers or professionals seeking rapid advancement.

Alternatively, some of the most worthwhile masters degrees are highly prized by employers. Fields such as Artificial Intelligence, Software Engineering, and Data Science continue to be in high demand.

For those wanting a flexible, cost-effective starting point, 2 year online degrees can build a strong foundation in computer science essentials, opening doors to entry-level IT roles or further studies.