Lukasz Szpruch
Scholar

Lukasz Szpruch

Google Scholar ID: ljeA6CMAAAAJ
University of Edinburgh and The Alan Turing Institute
Machine learningReinforcement LearningStochastic ControlQuantitative FinanceStatistical Sampling
Citations & Impact
All-time
Citations
3,389
 
H-index
32
 
i10-index
54
 
Publications
20
 
Co-authors
10
list available
Contact
No contact links provided.
Resume (English only)
Academic Achievements
  • He has published numerous papers on preprint platforms such as arXiv and SSRN. His research topics include Polyak-Lojasiewicz inequality, synthetic data, deep learning in finance, policy gradient convergence, exploration-exploitation trade-off, and more. Some of his papers are collaborative works with other researchers.
Research Experience
  • His broad research interests span probability theory, stochastic analysis, and theoretical machine learning. He is currently researching the mathematical foundation of deep learning, mean-field models, (inverse) reinforcement learning, game theory and multiagent systems, sampling and optimization algorithms, computational optimal transport, and the theory of gradient flows. He is also interested in applications of these areas in finance and economics.
Education
  • Before joining Edinburgh, he was a Nomura Junior Research Fellow at the Institute of Mathematics, University of Oxford.
Background
  • Professor at the School of Mathematics, University of Edinburgh, and Programme Director for Finance and Economics at The Alan Turing Institute. At Turing, he provides academic leadership for partnerships with the National Office for Statistics, Accenture, Bill and Melinda Gates Foundation, and HSBC. He is the Principal Investigator of the FAIR research programme on responsible adoption of AI in the financial services industry. He is also a co-Investigator of the UK Centre for Greening Finance & Investment (CGFI) and an affiliated member of the Oxford-Man Institute for Quantitative Finance.
Miscellany
  • Personal interests and hobbies are not mentioned in the provided HTML content.