Roy Frostig
- Artificial Intelligence top 1%
- Computer Vision and Pattern Recognition top 5%
- Information Systems top 5%
- Management Science and Operations Research top 10%
- Molecular Biology
- Co-authors
- Percy LiangJonathan BerantAndrew ChouMatthew JohnsonChris LearyYoram SingerAmit DanielyAaron Sidford
- Topics
- Sparse and Compressive Sensing Techniques (2 papers)Machine Learning and Algorithms (2 papers)Stochastic Gradient Optimization Techniques (2 papers)
- Journals
- Genome ResearchProceedings of the ACM on Programming LanguagesarXiv (Cornell University)
- Partner nations
- United States
In The Last Decade
Roy Frostig
9 papers receiving 875 citations
Hit Papers
Peers
Comparison fields: 5 of 85
- Artificial Intelligence 846
- Computer Vision and Pattern Recognition 252
- Information Systems 112
- Management Science and Operations Research 46
- Molecular Biology 28
Countries citing papers authored by Roy Frostig
This map shows the geographic impact of Roy Frostig'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 Roy Frostig with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Roy Frostig more than expected).
Fields of papers citing papers by Roy Frostig
This network shows the impact of papers produced by Roy Frostig. 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 Roy Frostig. The network helps show where Roy Frostig may publish in the future.
Co-authorship network of co-authors of Roy Frostig
This figure shows the co-authorship network connecting the top 25 collaborators of Roy Frostig. A scholar is included among the top collaborators of Roy Frostig 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 Roy Frostig. Roy Frostig is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 11 | |
| 2 | 0 | |
| 3 | 3 | |
| 4 | 3 | |
| 5 | Compiling machine learning programs via high-level tracing | 71 |
| 6 | Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity | 23 |
| 7 | Competing with the Empirical Risk Minimizer in a Single Pass | 24 |
| 8 | Simple MAP Inference via Low-Rank Relaxations | 3 |
| 9 | 11 | |
| 10 | Semantic Parsing on Freebase from Question-Answer Pairsbreakdown → | 804 |
About Roy Frostig
Roy Frostig is a scholar working on Software, Artificial Intelligence and Computational Theory and Mathematics, having authored 10 papers that have together received 953 indexed citations. Recurring topics across this work include Sparse and Compressive Sensing Techniques (2 papers), Machine Learning and Algorithms (2 papers) and Stochastic Gradient Optimization Techniques (2 papers). The work is most often cited by research in Artificial Intelligence (846 citations), Computer Vision and Pattern Recognition (252 citations) and Computational Mathematics (4 citations). Roy Frostig has collaborated with scholars based in United States. Frequent co-authors include Percy Liang, Jonathan Berant, Andrew Chou, Matthew Johnson, Chris Leary, Yoram Singer, Amit Daniely, Aaron Sidford, Rong Ge and Sham M. Kakade. Their work appears in journals such as Genome Research, Proceedings of the ACM on Programming Languages 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.