Tengyu Ma
About
In The Last Decade
Tengyu Ma
42 papers receiving 1.7k citations
Hit Papers
Peers
Comparison fields: 5 of 134
- Artificial Intelligence 956
- Computer Vision and Pattern Recognition 735
- Media Technology 229
- Information Systems 129
- Molecular Biology 89
Countries citing papers authored by Tengyu Ma
This map shows the geographic impact of Tengyu Ma's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Tengyu Ma with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Tengyu Ma more than expected).
Fields of papers citing papers by Tengyu Ma
This network shows the impact of papers produced by Tengyu Ma. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Tengyu Ma. The network helps show where Tengyu Ma may publish in the future.
Co-authorship network of co-authors of Tengyu Ma
This figure shows the co-authorship network connecting the top 25 collaborators of Tengyu Ma. A scholar is included among the top collaborators of Tengyu Ma based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Tengyu Ma. Tengyu Ma is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 4 | |
| 2 | 0 | |
| 3 | Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization | 2 |
| 4 | Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin | 2 |
| 5 | Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK | 1 |
| 6 | Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data | 32 |
| 7 | MOPO: Model-based Offline Policy Optimization | 7 |
| 8 | Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling | 2 |
| 9 | Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks | 6 |
| 10 | Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel | 16 |
| 11 | Bootstrapping the Expressivity with Model-based Planning | 1 |
| 12 | Gradient Descent Learns Linear Dynamical Systems | 42 |
| 13 | Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees. | 3 |
| 14 | Distributed stochastic variance reduced gradient methods by sampling extra data with replacement | 31 |
| 15 | A Simple but Tough-to-Beat Baseline for Sentence Embeddings breakdown → | 506 |
| 16 | Finding Approximate Local Minima for Nonconvex Optimization in Linear Time. | 12 |
| 17 | Finding Local Minima for Nonconvex Optimization in Linear Time | 3 |
| 18 | Distributed Stochastic Variance Reduced Gradient Methods. | 5 |
| 19 | Lower Bound for High-Dimensional Statistical Learning Problem via Direct-Sum Theorem. | 1 |
| 20 | 27 |
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.