Filip Hanzely
- Artificial Intelligence
- Computational Mechanics
- Economics and Econometrics
- Statistical and Nonlinear Physics
- Computational Theory and Mathematics
- Co-authors
- Peter RichtárikAnna KrakovskáLin XiaoEduard GorbunovKonstantin MishchenkoSamuel HorváthJingwei LiangDmitry Kovalev
- Topics
- Stochastic Gradient Optimization Techniques (5 papers)Sparse and Compressive Sensing Techniques (3 papers)Gaussian Processes and Bayesian Inference (1 paper)
- Journals
- IEEE Transactions on Signal ProcessingPhysical review. EComputational Optimization and Applications
- Partner nations
- Saudi ArabiaUnited KingdomRussia
In The Last Decade
Filip Hanzely
8 papers receiving 61 citations
Peers
Comparison fields: 5 of 41
- Artificial Intelligence 27
- Computational Mechanics 16
- Economics and Econometrics 11
- Statistical and Nonlinear Physics 11
- Computational Theory and Mathematics 10
Countries citing papers authored by Filip Hanzely
This map shows the geographic impact of Filip Hanzely'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 Filip Hanzely with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Filip Hanzely more than expected).
Fields of papers citing papers by Filip Hanzely
This network shows the impact of papers produced by Filip Hanzely. 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 Filip Hanzely. The network helps show where Filip Hanzely may publish in the future.
Co-authorship network of co-authors of Filip Hanzely
This figure shows the co-authorship network connecting the top 25 collaborators of Filip Hanzely. A scholar is included among the top collaborators of Filip Hanzely 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 Filip Hanzely. Filip Hanzely is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 18 | |
| 2 | Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems | 1 |
| 3 | 99% of Worker-Master Communication in Distributed Optimization Is Not Needed. | 3 |
| 4 | Lower Bounds and Optimal Algorithms for Personalized Federated Learning | 2 |
| 5 | 4 | |
| 6 | Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108 | 11 |
| 7 | SEGA: Variance Reduction via Gradient Sketching | 4 |
| 8 | 20 |
About Filip Hanzely
Filip Hanzely is a scholar working on Artificial Intelligence, Computational Mechanics and Statistics and Probability, having authored 8 papers that have together received 63 indexed citations. Recurring topics across this work include Stochastic Gradient Optimization Techniques (5 papers), Sparse and Compressive Sensing Techniques (3 papers) and Gaussian Processes and Bayesian Inference (1 paper). The work is most often cited by research in Computational Mathematics (1 citation), Numerical Analysis (6 citations) and Statistical and Nonlinear Physics (11 citations). Filip Hanzely has collaborated with scholars based in Saudi Arabia, United Kingdom and Russia. Frequent co-authors include Peter Richtárik, Anna Krakovská, Lin Xiao, Eduard Gorbunov, Konstantin Mishchenko, Samuel Horváth, Jingwei Liang and Dmitry Kovalev. Their work appears in journals such as IEEE Transactions on Signal Processing, Physical review. E and Computational Optimization and Applications.
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.