2026 Zeyuan Allen-Zhu: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	35	11485	11157	4721	4518	95	7878

Zeyuan Allen-Zhu publication distribution in Computer Science in 2026

The chart shows the distribution of publications by all Research.com ranked scientists in the field of Computer Science in 2026. The highlighted bar marks where Zeyuan Allen-Zhu sits on this spectrum.

32 publications 991+

This scientist: 95 publications — 7th percentile

7% of scientists in this discipline score the same or lower.

The last bar groups every scientist with 991 publications or more.

Zeyuan Allen-Zhu D-index placement in Computer Science in 2026

The chart shows the D-index (discipline H-index) distribution of Computer Science scientists ranked by Research.com in 2026. The highlighted bar marks where Zeyuan Allen-Zhu sits on this spectrum.

30 D-Index 131+

This scientist: 35 D-Index — 20th percentile

20% of scientists in this discipline score the same or lower.

The last bar groups every scientist with 131 D-Index or more.

Overview

Zeyuan Allen-Zhu is affiliated with Meta Platforms, Inc. in the United States. Their research primarily focuses on fields related to computer science, with a strong emphasis on artificial intelligence.

The main areas of study covered in their work include:

Artificial Intelligence
Computer Vision and Pattern Recognition
Computational Mechanics
Statistical and Nonlinear Physics
Information Systems

Major topics explored within these areas involve:

Natural Language Processing Techniques
Topic Modeling
Machine Learning and Algorithms
Stochastic Gradient Optimization Techniques
Adversarial Robustness in Machine Learning
Domain Adaptation and Few-Shot Learning
Sparse and Compressive Sensing Techniques

The scientist has contributed numerous publications, with a strong presence in the following venues:

arXiv (Cornell University)
SSRN Electronic Journal
Mathematical Programming

Best Publications

LoRA: Low-Rank Adaptation of Large Language Models.

Edward J. Hu;Yelong Shen;Phillip Wallis;Zeyuan Allen-Zhu

2371
Citations
A Convergence Theory for Deep Learning via Over-Parameterization

Zeyuan Allen-Zhu;Yuanzhi Li;Zhao Song

821
Citations
A Convergence Theory for Deep Learning via Over-Parameterization

Zeyuan Allen-Zhu;Yuanzhi Li;Zhao Song

616
Citations
Katyusha: The First Direct Acceleration of Stochastic Gradient Methods

Zeyuan Allen-Zhu

508
Citations
Is Q-learning Provably Efficient?

Chi Jin;Zeyuan Allen-Zhu;Sebastien Bubeck;Michael I. Jordan

462
Citations
Variance reduction for faster non-convex optimization

Zeyuan Allen-Zhu;Elad Hazan

342
Citations
A simple, combinatorial algorithm for solving SDD systems in nearly-linear time

Jonathan A. Kelner;Lorenzo Orecchia;Aaron Sidford;Zeyuan Allen Zhu

261
Citations
Natasha 2: Faster Non-Convex Optimization Than SGD

Zeyuan Allen-Zhu

220
Citations
Finding approximate local minima faster than gradient descent

Naman Agarwal;Zeyuan Allen-Zhu;Brian Bullins;Elad Hazan

211
Citations
Byzantine Stochastic Gradient Descent

Dan Alistarh;Zeyuan Allen-Zhu;Jerry Li

208
Citations
Asymptotically optimal strategy-proof mechanisms for two-facility games

Pinyan Lu;Xiaorui Sun;Yajun Wang;Zeyuan Allen Zhu

190
Citations
Improved SVRG for non-strongly-convex or sum-of-non-convex objectives

Zeyuan Allen-Zhu;Yang Yuan

177
Citations
Even faster accelerated coordinate descent using non-uniform sampling

Zeyuan Allen-Zhu;Zheng Qu;Peter Richtárik;Yang Yuan

166
Citations
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers

Zeyuan Allen-Zhu;Yuanzhi Li;Yingyu Liang

164
Citations
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning.

Zeyuan Allen-Zhu;Yuanzhi Li

163
Citations
Variance Reduction for Faster Non-Convex Optimization

Zeyuan Allen-Zhu;Elad Hazan

157
Citations
On the Convergence Rate of Training Recurrent Neural Networks

Zeyuan Allen-Zhu;Yuanzhi Li;Zhao Song

134
Citations
What Can ResNet Learn Efficiently, Going Beyond Kernels?

Zeyuan Allen-Zhu;Yuanzhi Li

124
Citations
A novel click model and its applications to online advertising

Zeyuan Allen Zhu;Weizhu Chen;Tom Minka;Chenguang Zhu

124
Citations
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers

Unknown

119
Citations
Randomized accuracy-aware program transformations for efficient approximate computations

Zeyuan Allen Zhu;Sasa Misailovic;Jonathan A. Kelner;Martin Rinard

118
Citations
Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent

Unknown

118
Citations
NEON2: Finding Local Minima via First-Order Oracles

Zeyuan Allen-Zhu;Yuanzhi Li

111
Citations
A Local Algorithm for Finding Well-Connected Clusters

Zeyuan Allen Zhu;Silvio Lattanzi;Vahab Mirrokni

106
Citations
LazySVD: Even Faster SVD Decomposition Yet Without Agonizing Pain

Zeyuan Allen-Zhu;Yuanzhi Li

105
Citations
Feature Purification: How Adversarial Training Performs Robust Deep Learning

Zeyuan Allen-Zhu;Yuanzhi Li

103
Citations
Much Faster Algorithms for Matrix Scaling

Zeyuan Allen-Zhu;Yuanzhi Li;Rafael Oliveira;Avi Wigderson

99
Citations
P-packSVM: Parallel Primal grAdient desCent Kernel SVM

Zeyuan Allen Zhu;Weizhu Chen;Gang Wang;Chenguang Zhu

97
Citations
First Efficient Convergence for Streaming k-PCA: A Global, Gap-Free, and Near-Optimal Rate

Zeyuan Allen-Zhu;Yuanzhi Li

88
Citations
Backward Feature Correction: How Deep Learning Performs Deep Learning

Zeyuan Allen-Zhu;Yuanzhi Li

86
Citations
Byzantine Stochastic Gradient Descent

Dan Alistarh;Zeyuan Allen-Zhu;Jerry Li

73
Citations
How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD

Zeyuan Allen-Zhu

45
Citations
Even Faster SVD Decomposition Yet Without Agonizing Pain

Zeyuan Allen Zhu;Yuanzhi Li

7
Citations

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

Related Online Degrees & Career Pathways

Choosing to study Computer Science in the USA opens up a variety of flexible education and career options. Many students look for cheap online colleges to balance quality education with affordability. These institutions offer accessible learning pathways that don't compromise academic rigor.

If GPA requirements are a concern, it’s worth exploring online graduate schools with low gpa requirements. These colleges provide opportunities for students with unconventional academic histories to pursue advanced Computer Science degrees.

Accelerated learning is also gaining popularity. Many universities now feature computer science accelerated program options designed for those who want to advance their careers quickly.

Computer Science isn’t the only route—related degrees, like environmental science, can also unlock diverse career possibilities. To see what fields you could enter with such qualifications, discover what can you get with an environmental science degree.

From budget-friendly colleges to accelerated programs and flexible entry requirements, there are many online degree options to help launch your career in technology or other exciting sectors.