Suvrit Sra
About
In The Last Decade
Suvrit Sra
107 papers receiving 4.6k citations
Hit Papers
Peers
Comparison fields: 5 of 160
- Computer Vision and Pattern Recognition 2.3k
- Artificial Intelligence 1.9k
- Computational Mechanics 777
- Signal Processing 578
- Media Technology 347
Countries citing papers authored by Suvrit Sra
This map shows the geographic impact of Suvrit Sra'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 Suvrit Sra with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Suvrit Sra more than expected).
Fields of papers citing papers by Suvrit Sra
This network shows the impact of papers produced by Suvrit Sra. 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 Suvrit Sra. The network helps show where Suvrit Sra may publish in the future.
Co-authorship network of co-authors of Suvrit Sra
This figure shows the co-authorship network connecting the top 25 collaborators of Suvrit Sra. A scholar is included among the top collaborators of Suvrit Sra 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 Suvrit Sra. Suvrit Sra is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 2 | |
| 2 | Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? | 1 |
| 3 | Why are Adaptive Methods Good for Attention Models | 2 |
| 4 | 19 | |
| 5 | Flexible Modeling of Diversity with Strongly Log-Concave Distributions | 1 |
| 6 | Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity | 9 |
| 7 | Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator | 5 |
| 8 | Direct runge-kutta discretization achieves acceleration | 4 |
| 9 | A Critical View of Global Optimality in Deep Learning | 10 |
| 10 | Kronecker Determinantal Point Processes | 1 |
| 11 | 1 | |
| 12 | Gaussian quadrature for matrix inverse forms with applications | 3 |
| 13 | On variance reduction in stochastic gradient descent and its asynchronous variants | 22 |
| 14 | Fixed-point algorithms for determinantal point processes. | 1 |
| 15 | Fast Newton methods for the group fused lasso | 6 |
| 16 | A new metric on the manifold of kernel matrices with application to matrix geometric means | 68 |
| 17 | A scalable trust-region algorithm with application to mixed-norm regression | 18 |
| 18 | Efficient Large Scale Linear Programming Support Vector Machines | 1 |
| 19 | Clustering on the Unit Hypersphere using von Mises-Fisher Distributions breakdown → | 505 |
| 20 | Triangle Fixing Algorithms for the Metric Nearness Problem | 4 |
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.