This article was accepted into the corpus but its outbound wikilinks were never NER-processed — typical at the deepest BFS hop or when the run's entity cap was reached. No expansion funnel to show.
| Krzysztof Choromanski | |
|---|---|
| Name | Krzysztof Choromanski |
| Nationality | Polish |
| Fields | Computer Science, Machine Learning, Theoretical Computer Science |
| Institutions | Google Research, Stanford University, Princeton University, University of Warsaw |
Krzysztof Choromanski is a computer scientist known for work in theoretical computer science and machine learning, particularly randomized algorithms, kernel methods, and efficient approximations. He has held positions in academic and industry research institutions and contributed to algorithms for scalable learning, optimization, and large-scale data processing.
Choromanski was born and raised in Poland, where he completed early schooling before pursuing higher education at the University of Warsaw, a major Polish research university. He obtained graduate training that connected him with research groups at institutions such as Institute of Computer Science PAS, leading to doctoral studies influenced by mentors associated with Princeton University and Stanford University. His doctoral work intersected with topics studied at Massachusetts Institute of Technology and referenced frameworks developed at Carnegie Mellon University and University of Cambridge.
Choromanski has held roles at research centers and universities including appointments or collaborations with University of Warsaw, Princeton University, Stanford University, and later with industrial research labs such as Google Research. He interacted with researchers from Microsoft Research, Facebook AI Research, DeepMind, and academic groups at University of California, Berkeley and Columbia University. His career included visiting positions and joint projects with teams at ETH Zurich, University of Oxford, University of Toronto, and collaborations drawing expertise from Harvard University and Yale University.
His research spans randomized numerical linear algebra, kernel approximation, and efficient deep learning primitives, building on theories from Leslie Valiant-style computational learning and techniques used by scholars at Alan Turing Institute, Simons Institute for the Theory of Computing, and Courant Institute of Mathematical Sciences. He contributed methods related to randomized feature maps connected to work by researchers at Google Brain, advances in fast transforms inspired by Cooley–Tukey FFT algorithm developments, and scalable approximate algorithms with relevance to teams at Amazon Web Services and NVIDIA. Choromanski's contributions tie to foundational results from Noga Alon, Shafi Goldwasser, and Jon Kleinberg in probabilistic algorithms, and to contemporary topics pursued at OpenAI, Allen Institute for AI, and IBM Research. He developed techniques influencing applications in systems championed by Apache Software Foundation projects, and statistical methods aligned with approaches from Statistical Learning Theory proponents at École Polytechnique Fédérale de Lausanne and Technische Universität München.
Choromanski's work has been recognized by awards and fellowships associated with institutions such as Google Research, grants from agencies comparable to National Science Foundation, and honors tied to conferences including NeurIPS, ICML, and COLT. He received invitations to speak at venues organized by SIAM, the Association for Computing Machinery, and panels at International Congress of Mathematicians-adjacent workshops. His papers have been highlighted in proceedings linked to the IEEE and ACM.
His publications appear in flagship venues alongside authors affiliated with NeurIPS, ICML, COLT, STOC, and FOCS. Representative works include papers on randomized feature approximations influenced by prior art from Rahimi and Recht-style kernels, fast sketching methods related to algorithms studied at Stanford AI Lab, and contributions to transformer efficiency resonant with research by teams at Google Brain and OpenAI. He has coauthored articles with collaborators from Princeton University, Stanford University, University of Oxford, and industry groups at DeepMind and Microsoft Research.
Choromanski has supervised students and collaborated with postdoctoral researchers connected to programs at University of Warsaw, Princeton University, and Stanford University, contributing to curricula influenced by courses at Massachusetts Institute of Technology and University of California, Berkeley. He has participated in summer schools and workshops organized by Simons Institute for the Theory of Computing, Zuse Institute Berlin, and Les Houches-style programs, mentoring emerging researchers who later joined groups at Google Research, DeepMind, Facebook AI Research, and academic departments across Europe and North America.
Category:Polish computer scientists Category:Machine learning researchers