Kumar Kshitij Patel
- Artificial Intelligence
- Computer Networks and Communications
- Management Science and Operations Research
- Electrical and Electronic Engineering
- Computer Vision and Pattern Recognition
- Co-authors
- Sebastian U. StichTao LinMartin JaggiSayash KapoorPurushottam KarBrian BullinsH. Brendan McMahanNati Srebro
- Topics
- Stochastic Gradient Optimization Techniques (3 papers)Advanced Bandit Algorithms Research (2 papers)Machine Learning and Algorithms (1 paper)
- Cited by
- Artificial IntelligenceManagement Science and Operations ResearchComputer Networks and Communications
- Journals
- Machine LearningInfoscience (Ecole Polytechnique Fédérale de Lausanne)Neural Information Processing Systems
- Partner nations
- United StatesSwitzerlandIndia
In The Last Decade
Kumar Kshitij Patel
4 papers receiving 62 citations
Peers
Comparison fields: 5 of 16
- Artificial Intelligence 54
- Computer Networks and Communications 21
- Management Science and Operations Research 14
- Electrical and Electronic Engineering 13
- Computer Vision and Pattern Recognition 9
Countries citing papers authored by Kumar Kshitij Patel
This map shows the geographic impact of Kumar Kshitij Patel'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 Kumar Kshitij Patel with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Kumar Kshitij Patel more than expected).
Fields of papers citing papers by Kumar Kshitij Patel
This network shows the impact of papers produced by Kumar Kshitij Patel. 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 Kumar Kshitij Patel. The network helps show where Kumar Kshitij Patel may publish in the future.
Co-authorship network of co-authors of Kumar Kshitij Patel
This figure shows the co-authorship network connecting the top 25 collaborators of Kumar Kshitij Patel. A scholar is included among the top collaborators of Kumar Kshitij Patel 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 Kumar Kshitij Patel. Kumar Kshitij Patel is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | Don't Use Large Mini-batches, Use Local SGD | 21 |
| 2 | Is Local SGD Better than Minibatch SGD | 23 |
| 3 | Communication trade-offs for Local-SGD with large step size | 4 |
| 4 | 15 |
About Kumar Kshitij Patel
Kumar Kshitij Patel is a scholar working on Management Science and Operations Research, Artificial Intelligence and Computer Vision and Pattern Recognition, having authored 4 papers that have together received 63 indexed citations. Recurring topics across this work include Stochastic Gradient Optimization Techniques (3 papers), Advanced Bandit Algorithms Research (2 papers) and Machine Learning and Algorithms (1 paper). The work is most often cited by research in Artificial Intelligence (54 citations), Management Science and Operations Research (14 citations) and Computer Networks and Communications (21 citations). Kumar Kshitij Patel has collaborated with scholars based in United States, Switzerland and India. Frequent co-authors include Sebastian U. Stich, Tao Lin, Martin Jaggi, Sayash Kapoor, Purushottam Kar, Brian Bullins, H. Brendan McMahan, Nati Srebro, Blake Woodworth and Ohad Shamir. Their work appears in journals such as Machine Learning, Infoscience (Ecole Polytechnique Fédérale de Lausanne) and Neural Information Processing Systems.
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.