Aurko Roy
Impact in
- Artificial Intelligence top 5%
- Adversarial Robustness in Machine Learning
- Anomaly Detection Techniques and Applications
- Domain Adaptation and Few-Shot Learning
- Topic Modeling
- Signal Processing top 10%
- Advanced Malware Detection Techniques
Papers in
-
- Complexity and Algorithms in Graphs 3
- Advanced Graph Theory Research 2
-
- Advanced Optimization Algorithms Research 2
- Co-authors
- Colin Raffel (2 shared papers)Ian Goodfellow (2 shared papers)Jacob Buckman (1 shared paper)Łukasz Kaiser (1 shared paper)Samy Bengio (1 shared paper)Ofir Nachum (1 shared paper)David Berthelot (1 shared paper)Sebastian Pokutta (3 shared papers)
- Journals
- Mathematical Programming (2 papers)Journal of Machine Learning Research (1 paper)International Conference on Learning Representations (1 paper)arXiv (Cornell University) (2 papers)
- Partner nations
- United States
In The Last Decade
Aurko Roy
7 papers receiving 251 citations
Peers
Comparison fields: 5 of 54
- Artificial Intelligence 223
- Signal Processing 45
- Computer Vision and Pattern Recognition 85
- Hardware and Architecture 15
- Health Informatics 1
Countries citing papers authored by Aurko Roy
This map shows the geographic impact of Aurko Roy'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 Aurko Roy with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Aurko Roy more than expected).
Fields of papers citing papers by Aurko Roy
This network shows the impact of papers produced by Aurko Roy. 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 Aurko Roy. The network helps show where Aurko Roy may publish in the future.
Co-authors
The 13 scholars most cited alongside Aurko Roy, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | Thermometer Encoding: One Hot Way To Resist Adversarial Examples | 2018 | 194 |
| 2 | Learning to Remember Rare Events | 2017 | 32 |
| 3 | 2018 | 24 | |
| 4 | 2016 | 9 | |
| 5 | Towards a better understanding of Vector Quantized Autoencoders | 2018 | 7 |
| 6 | 2016 | 1 | |
| 7 | 2018 | 1 |
About Aurko Roy
Aurko Roy is a scholar working on Computational Theory and Mathematics, Numerical Analysis, Computer Vision and Pattern Recognition, Artificial Intelligence and Statistical and Nonlinear Physics, having authored 7 papers that have together received 268 indexed citations. Recurring topics across this work include Complexity and Algorithms in Graphs (3 papers), Adversarial Robustness in Machine Learning (2 papers), Advanced Optimization Algorithms Research (2 papers), Advanced Graph Theory Research (2 papers), Data Management and Algorithms (1 paper), Model Reduction and Neural Networks (1 paper), Generative Adversarial Networks and Image Synthesis (1 paper) and Advanced Data Compression Techniques (1 paper). The work is most often cited by research in Artificial Intelligence (223 citations), Signal Processing (45 citations), Computer Vision and Pattern Recognition (85 citations), Hardware and Architecture (15 citations) and Health Informatics (1 citation). Aurko Roy has collaborated with scholars based in United States. Frequent co-authors include Colin Raffel, Ian Goodfellow, Jacob Buckman, Łukasz Kaiser, Samy Bengio, Ofir Nachum, David Berthelot, Sebastian Pokutta, Niki Parmar and Ashish Vaswani. Their work appears in journals such as Mathematical Programming, Journal of Machine Learning Research, International Conference on Learning Representations 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.