Nati Srebro
- Artificial Intelligence top 5%
- Computational Mechanics top 10%
- Computer Vision and Pattern Recognition top 10%
- Computer Networks and Communications top 10%
- Management Science and Operations Research top 10%
- Co-authors
- Ohad ShamirTong ZhangKarthik SridharanAndrew CotterAmbuj TewariMartin TakáčShai Shalev‐ShwartzPeter Richtárik
- Topics
- Stochastic Gradient Optimization Techniques (6 papers)Machine Learning and Algorithms (5 papers)Advanced Bandit Algorithms Research (5 papers)
- Journals
- OpenBU/Boston University Institutional Repository (Boston University)Rare & Special e-Zone (The Hong Kong University of Science and Technology)arXiv (Cornell University)
- Partner nations
- United StatesIsraelUnited Kingdom
In The Last Decade
Nati Srebro
15 papers receiving 394 citations
Peers
Comparison fields: 5 of 58
- Artificial Intelligence 299
- Computational Mechanics 135
- Computer Vision and Pattern Recognition 86
- Computer Networks and Communications 85
- Management Science and Operations Research 44
Countries citing papers authored by Nati Srebro
This map shows the geographic impact of Nati Srebro'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 Nati Srebro with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Nati Srebro more than expected).
Fields of papers citing papers by Nati Srebro
This network shows the impact of papers produced by Nati Srebro. 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 Nati Srebro. The network helps show where Nati Srebro may publish in the future.
Co-authorship network of co-authors of Nati Srebro
This figure shows the co-authorship network connecting the top 25 collaborators of Nati Srebro. A scholar is included among the top collaborators of Nati Srebro 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 Nati Srebro. Nati Srebro is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent | 1 |
| 2 | Fair Learning with Private Demographic Data | 1 |
| 3 | Is Local SGD Better than Minibatch SGD | 23 |
| 4 | 16 | |
| 5 | 3 | |
| 6 | Normalized Spectral Map Synchronization | 24 |
| 7 | Communication-Efficient Distributed Optimization using an Approximate Newton-type Method | 138 |
| 8 | Mini-Batch Primal and Dual Methods for SVMs | 31 |
| 9 | Learning Optimally Sparse Support Vector Machines | 24 |
| 10 | 1 | |
| 11 | Characterizing the Sample Complexity of Large-Margin Learning With Second-Order Statistics | 1 |
| 12 | Beating SGD: Learning SVMs in Sublinear Time | 22 |
| 13 | 98 | |
| 14 | 28 | |
| 15 | On the Interaction between Norm and Dimensionality: Multiple Regimes in Learning | 3 |
| 16 | A Dynamic Data Structure for Checking Hyperacyclicity | 0 |
About Nati Srebro
Nati Srebro is a scholar working on Management Science and Operations Research, Artificial Intelligence and Signal Processing, having authored 16 papers that have together received 414 indexed citations. Recurring topics across this work include Stochastic Gradient Optimization Techniques (6 papers), Machine Learning and Algorithms (5 papers) and Advanced Bandit Algorithms Research (5 papers). The work is most often cited by research in Artificial Intelligence (299 citations), Computational Mechanics (135 citations) and Computational Mathematics (3 citations). Nati Srebro has collaborated with scholars based in United States, Israel and United Kingdom. Frequent co-authors include Ohad Shamir, Tong Zhang, Karthik Sridharan, Andrew Cotter, Ambuj Tewari, Martin Takáč, Shai Shalev‐Shwartz, Peter Richtárik, Elad Hazan and Tomer Koren. Their work appears in journals such as OpenBU/Boston University Institutional Repository (Boston University), Rare & Special e-Zone (The Hong Kong University of Science and Technology) and arXiv (Cornell University).
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.