Scholar
Omar Rivasplata
Google Scholar ID: sYdUCVQAAAAJ
University of Manchester
Citations & Impact
Citations
684
H-index
10
i10-index
10
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Member of the European Laboratory for Learning and Intelligent Systems (ELLIS), based at the ELLIS Unit Manchester. Member of the London Mathematical Society (LMS) and LMS Regional Representative for the North. Fellow of the Institute of Mathematics and its Applications (IMA). Fellow of the Royal Statistical Society (RSS), committee member of the RSS section on Computational Statistics and Machine Learning (CSML), and part of the RSS AI Task Force.
Research Experience
- Currently an Associate Professor (Senior Lecturer) in Machine Learning at the Department of Computer Science, University of Manchester. Also an academic staff member at the Manchester Centre for AI Fundamentals and a supervisor in the UKRI AI CDT in Decision Making for Complex Systems. Previously, a Senior Research Fellow at the Department of Statistical Science, UCL, where he created and led the DELTA research group. Worked at UCL Computer Science and DeepMind, collaborating with many distinguished ML/AI researchers.
Education
- Conducted research in Statistical Learning at the Department of Computer Science, University College London, with a dissertation titled 'PAC-Bayesian Computation', sponsored by DeepMind. Also held a fixed-term position at DeepMind for three years.
Background
- Research interests include Statistical Learning Theory, Machine Learning, AI, Mathematics, Probability and Statistics. Focuses on certifying AI predictions with high confidence. Research spans the theory and practice of machine learning, particularly its mathematical and statistical foundations. Has a broad interest in optimizing and certifying machine learning models. Previously led or contributed to projects on offline reinforcement learning, generative models, PAC-Bayes bounds for deep learning and kernel classifiers, among others.
Miscellany
- Has a particular interest in optimization, viewing it as a pervasive theme across machine learning theory and practice. Believes that while optimization is important, certification is crucial for true learning.
Co-authors