Brian Bullins
- Artificial Intelligence top 10%
- Computational Mechanics top 10%
- Numerical Analysis top 10%
- Computational Theory and Mathematics
- Computer Networks and Communications
- Co-authors
- Elad HazanNaman AgarwalTengyu MaZeyuan Allen-ZhuCoralia CartisBlake WoodworthOhad ShamirH. Brendan McMahan
- Topics
- Stochastic Gradient Optimization Techniques (11 papers)Sparse and Compressive Sensing Techniques (9 papers)Machine Learning and Algorithms (5 papers)
- Journals
- SIAM Journal on OptimizationLinear Algebra and its ApplicationsOxford University Research Archive (ORA) (University of Oxford)
- Partner nations
- United StatesIsraelSwitzerland
In The Last Decade
Brian Bullins
14 papers receiving 146 citations
Peers
Comparison fields: 5 of 45
- Artificial Intelligence 98
- Computational Mechanics 74
- Numerical Analysis 37
- Computational Theory and Mathematics 30
- Computer Networks and Communications 21
Countries citing papers authored by Brian Bullins
This map shows the geographic impact of Brian Bullins'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 Brian Bullins with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Brian Bullins more than expected).
Fields of papers citing papers by Brian Bullins
This network shows the impact of papers produced by Brian Bullins. 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 Brian Bullins. The network helps show where Brian Bullins may publish in the future.
Co-authorship network of co-authors of Brian Bullins
This figure shows the co-authorship network connecting the top 25 collaborators of Brian Bullins. A scholar is included among the top collaborators of Brian Bullins 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 Brian Bullins. Brian Bullins is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 10 | |
| 2 | 5 | |
| 3 | 2 | |
| 4 | Highly smooth minimization of non-smooth problems | 1 |
| 5 | Adaptive regularization with cubics on manifolds | 19 |
| 6 | Is Local SGD Better than Minibatch SGD | 23 |
| 7 | 9 | |
| 8 | Adaptive regularization with cubics on manifolds with a first-order analysis | 2 |
| 9 | The Case for Full-Matrix Adaptive Regularization | 0 |
| 10 | 2 | |
| 11 | 53 | |
| 12 | Finding Approximate Local Minima for Nonconvex Optimization in Linear Time. | 12 |
| 13 | Finding Local Minima for Nonconvex Optimization in Linear Time | 3 |
| 14 | The Limits of Learning with Missing Data | 5 |
| 15 | 10 |
About Brian Bullins
Brian Bullins is a scholar working on Computational Mechanics, Computational Theory and Mathematics and Artificial Intelligence, having authored 15 papers that have together received 156 indexed citations. Recurring topics across this work include Stochastic Gradient Optimization Techniques (11 papers), Sparse and Compressive Sensing Techniques (9 papers) and Machine Learning and Algorithms (5 papers). The work is most often cited by research in Numerical Analysis (37 citations), Computational Mathematics (3 citations) and Computational Mechanics (74 citations). Brian Bullins has collaborated with scholars based in United States, Israel and Switzerland. Frequent co-authors include Elad Hazan, Naman Agarwal, Tengyu Ma, Zeyuan Allen-Zhu, Coralia Cartis, Blake Woodworth, Ohad Shamir, H. Brendan McMahan, Kumar Kshitij Patel and Nati Srebro. Their work appears in journals such as SIAM Journal on Optimization, Linear Algebra and its Applications and Oxford University Research Archive (ORA) (University of Oxford).
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.