Ilya Tolstikhin
- Computer Vision and Pattern Recognition top 5%
- Artificial Intelligence top 5%
- Signal Processing
- Statistical and Nonlinear Physics
- Control and Systems Engineering
- Co-authors
- Bernhard SchölkopfOlivier BousquetSylvain GellyCarl-Johann Simon-GabrielBharath K. SriperumbudurYevgeny SeldinPaul K. RubensteinIbrahim Alabdulmohsin
- Topics
- Generative Adversarial Networks and Image Synthesis (4 papers)Machine Learning and Algorithms (3 papers)Bayesian Modeling and Causal Inference (2 papers)
- Journals
- Apollo (University of Cambridge)arXiv (Cornell University)Neural Information Processing Systems
- Partner nations
- GermanyUnited StatesAustralia
In The Last Decade
Ilya Tolstikhin
8 papers receiving 377 citations
Hit Papers
Peers
Comparison fields: 5 of 71
- Computer Vision and Pattern Recognition 247
- Artificial Intelligence 219
- Signal Processing 42
- Statistical and Nonlinear Physics 33
- Control and Systems Engineering 23
Countries citing papers authored by Ilya Tolstikhin
This map shows the geographic impact of Ilya Tolstikhin'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 Ilya Tolstikhin with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ilya Tolstikhin more than expected).
Fields of papers citing papers by Ilya Tolstikhin
This network shows the impact of papers produced by Ilya Tolstikhin. 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 Ilya Tolstikhin. The network helps show where Ilya Tolstikhin may publish in the future.
Co-authorship network of co-authors of Ilya Tolstikhin
This figure shows the co-authorship network connecting the top 25 collaborators of Ilya Tolstikhin. A scholar is included among the top collaborators of Ilya Tolstikhin 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 Ilya Tolstikhin. Ilya Tolstikhin is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | What Do Neural Networks Learn When Trained With Random Labels | 1 |
| 2 | Learning Disentangled Representations with Wasserstein Auto-Encoders | 3 |
| 3 | Wasserstein Auto-Encodersbreakdown → | 262 |
| 4 | Wasserstein Auto-Encoders: Latent Dimensionality and Random Encoders | 3 |
| 5 | 72 | |
| 6 | Minimax estimation of maximum mean discrepancy with radial kernels | 38 |
| 7 | 4 | |
| 8 | Towards a Learning Theory of Causation | 0 |
| 9 | PAC-Bayes-empirical-Bernstein inequality | 15 |
About Ilya Tolstikhin
Ilya Tolstikhin is a scholar working on Computer Graphics and Computer-Aided Design, Statistics and Probability and Artificial Intelligence, having authored 9 papers that have together received 398 indexed citations. Recurring topics across this work include Generative Adversarial Networks and Image Synthesis (4 papers), Machine Learning and Algorithms (3 papers) and Bayesian Modeling and Causal Inference (2 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (247 citations), Artificial Intelligence (219 citations) and Signal Processing (42 citations). Ilya Tolstikhin has collaborated with scholars based in Germany, United States and Australia. Frequent co-authors include Bernhard Schölkopf, Olivier Bousquet, Sylvain Gelly, Carl-Johann Simon-Gabriel, Bharath K. Sriperumbudur, Yevgeny Seldin, Paul K. Rubenstein, Ibrahim Alabdulmohsin, Daniel Keysers and David López-Paz. Their work appears in journals such as Apollo (University of Cambridge), arXiv (Cornell University) and Neural Information Processing Systems.
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.