Sashank J. Reddi
- Artificial Intelligence top 2%
- Computer Vision and Pattern Recognition top 10%
- Computational Mechanics top 10%
- Statistics and Probability top 5%
- Computer Networks and Communications
- Co-authors
- Satyen KaleBarnabás PóczosSuvrit SraSanjiv KumarSai Praneeth KarimireddyAnanda Theertha SureshMehryar MohriSebastian U. Stich
- Topics
- Stochastic Gradient Optimization Techniques (13 papers)Sparse and Compressive Sensing Techniques (8 papers)Machine Learning and Algorithms (5 papers)
- Journals
- HAL (Le Centre pour la Communication Scientifique Directe)arXiv (Cornell University)Figshare
- Partner nations
- United StatesSwitzerlandIndia
In The Last Decade
Sashank J. Reddi
28 papers receiving 566 citations
Peers
Comparison fields: 5 of 82
- Artificial Intelligence 484
- Computer Vision and Pattern Recognition 106
- Computational Mechanics 102
- Statistics and Probability 64
- Computer Networks and Communications 50
Countries citing papers authored by Sashank J. Reddi
This map shows the geographic impact of Sashank J. Reddi'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 Sashank J. Reddi with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Sashank J. Reddi more than expected).
Fields of papers citing papers by Sashank J. Reddi
This network shows the impact of papers produced by Sashank J. Reddi. 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 Sashank J. Reddi. The network helps show where Sashank J. Reddi may publish in the future.
Co-authorship network of co-authors of Sashank J. Reddi
This figure shows the co-authorship network connecting the top 25 collaborators of Sashank J. Reddi. A scholar is included among the top collaborators of Sashank J. Reddi 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 Sashank J. Reddi. Sashank J. Reddi is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | Breaking the centralized barrier for cross-device federated learning | 25 |
| 2 | Efficient Training of Retrieval Models using Negative Cache | 2 |
| 3 | A statistical perspective on distillation | 5 |
| 4 | RankDistil: Knowledge Distillation for Ranking | 4 |
| 5 | Can gradient clipping mitigate label noise | 28 |
| 6 | Why are Adaptive Methods Good for Attention Models | 2 |
| 7 | Learning to Learn by Zeroth-Order Oracle | 1 |
| 8 | Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces | 15 |
| 9 | Multilabel reductions: what is my loss optimising? | 9 |
| 10 | Why ADAM Beats SGD for Attention Models | 23 |
| 11 | Adaptive Methods for Nonconvex Optimization | 102 |
| 12 | 0 | |
| 13 | 3 | |
| 14 | Proximal stochastic methods for nonsmooth nonconvex finite-sum optimization | 43 |
| 15 | 29 | |
| 16 | On variance reduction in stochastic gradient descent and its asynchronous variants | 22 |
| 17 | On the High Dimensional Power of a Linear-Time Two Sample Test under Mean-shift Alternatives | 6 |
| 18 | Communication efficient coresets for empirical loss minimization | 9 |
| 19 | Kernel MMD, the Median Heuristic and Distance Correlation in High Dimensions. | 4 |
| 20 | MAP estimation in Binary MRFs via Bipartite Multi-cuts | 0 |
About Sashank J. Reddi
Sashank J. Reddi is a scholar working on Statistics and Probability, Artificial Intelligence and Numerical Analysis, having authored 30 papers that have together received 592 indexed citations. Recurring topics across this work include Stochastic Gradient Optimization Techniques (13 papers), Sparse and Compressive Sensing Techniques (8 papers) and Machine Learning and Algorithms (5 papers). The work is most often cited by research in Artificial Intelligence (484 citations), Computational Mathematics (5 citations) and Statistics and Probability (64 citations). Sashank J. Reddi has collaborated with scholars based in United States, Switzerland and India. Frequent co-authors include Satyen Kale, Barnabás Póczos, Suvrit Sra, Sanjiv Kumar, Sai Praneeth Karimireddy, Ananda Theertha Suresh, Mehryar Mohri, Sebastian U. Stich, Manzil Zaheer and Alex Smola. Their work appears in journals such as HAL (Le Centre pour la Communication Scientifique Directe), arXiv (Cornell University) and Figshare.
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.