.
Omar_Portrait
Omar Rivasplata

Centre for AI Fundamentals
Department of Computer Science
University of Manchester

Noteworthy News   ‖   CV   ‖   Email: try or   ‖   Math Genealogy   ‖   Follow:          

Topics of Interest
Statistical Learning Theory.   Machine Learning.   AI.   Mathematics.   Probability and Statistics.  

About me and what I do
I certify AI predictions with high confidence.

My research is on machine learning, theory and practice. That said, I tend to have a broad interest in various aspects of the mathematical and statistical foundations of machine learning and AI in general. In the limit of tending to praxis, I work on designing strategies to train and certify machine learning models. Previously, I have led or been a contributor to projects on offline reinforcement learning, generative models, PAC-Bayes bounds for deep learning and kernel classifiers, among other.

The field of machine learning research is fascinating! One of the things I enjoy most about my work being the confluence of maths and stats, and computer experiments with collaborators, to answer questions about the optimisation and certification of machine learning models. Besides statistical learning I am interested also in online learning and reinforcement learning. Of course I am interested in deep learning, which is quite popular these days. Optimisation is a pervasive theme across machine learning theory and practice, though it comes up in such a variety of flavours and colours that it isn't boring. It reminds of the least action principle of Maupertuis, saying that "everything happens as if some quantity was to be made as small as possible." (This principle has lead the optimists to believe that we live in the best possible world.) But just optimisation doesn't quite do it for machine learning... to really be talking about learning one has to pay attention to learner's performance beyond the data used for training; so certification is very important!

These are my affiliations with learned sociaties:

*New Job*
From 1st of July 2024 I am Associate Professor (Senior Lecturer) in Machine Learning in the Department of Computer Science at the University of Manchester. Also, I am a member of the Centre for AI Fundamentals and a supervisor in the UKRI AI CDT in Decision Making for Complex Systems.

Before
For a couple of years and a half I was a Senior Research Fellow in the Department of Statistical Science at UCL, where I created and led the research group DELTA. Mine was one of two departments of the upcoming Institute for Mathematical and Statistical Sciences, the other one being the Department of Mathematics.

My dissertation PAC-Bayesian Computation was the result of my research studies in statistical learning at the Department of Computer Science, University College London, which were sponsored by DeepMind. In parallel with my research studies at UCL, I had a fixed-term position with DeepMind for three years.

Outstanding ML/AI people with whom I have worked at UCL Computer Science include David Barber, Marc Deisenroth, Mark Herbster, María Pérez-Ortiz, and John Shawe-Taylor.

Outstanding ML/AI people with whom I have worked at DeepMind include Marcus Hutter, Laurent Orseau, Ilja Kuzborskij, Csaba Szepesvári, András György from my own team; and many others from friend teams including Amal Rannen-Triki, Razvan Pascanu, Agnieszka Grabska-Barwińska, Thore Graepel, Arnaud Doucet, Benjamin Van Roy, and Geoffrey Irving.
My journey into ML research started at the Department of Computing Science, University of Alberta, where I spent a year and two months. During this time I started building my mental model of the ML field and fine-tuning my hyperparameters. My host was Rich Sutton in theory, but in practice I was working with Csaba Szepesvári.

Much Before
I spent some postdoc time with Mauricio Sacchi's group looking at optimization problems related to seismic signal analysis.

My PhD dissertation Smallest singular value of sparse random matrices was the result of my work with Sasha Litvak and Nicole Tomczak-Jaegermann.

My MSc thesis was about characterizatinos of reversibility for Brownian motion with drift, supervised by Byron Schmuland.

My BSc thesis was a fun project about repeated two-player games with incomplete information on one side.


Talks (sample)
  • Tighter risk certificates for (probabilistic) neural networks. UCL Centre for AI. Slides Video
  • Statistical Learning Theory: A Hitchhiker's Guide. NeurIPS 2018 Tutorial. (with J. Shawe-Taylor) Slides Video

Conference & Journal Papers
  • S.D. Mbacke and O. Rivasplata, A Note on the Convergence of Denoising Diffusion Probabilistic Models. TMLR 2024. PDF
  • B. Rodríguez Gálvez, O. Rivasplata, R. Thobaben, M. Skoglund, A note on generalization bounds for losses with finite moments. ISIT 2024. arXiv PDF
  • I. Kuzborskij, Cs. Szepesvári, O. Rivasplata, A. Rannen-Triki, R. Pascanu, On the Role of Optimization in Double Descent: A Least Squares Study. NeurIPS 2021. arXiv PDF
  • M. Pérez-Ortiz, O. Rivasplata, J. Shawe-Taylor, Cs. Szepesvári, Tighter risk certificates for neural networks. JMLR, 22, 227 (2021), 1-40. PDF / revised PDF / published PDF
  • L. Orseau, M. Hutter, O. Rivasplata, Logarithmic pruning is all you need. NeurIPS 2020 . PDF
  • O. Rivasplata, I. Kuzborskij, Cs. Szepesvári, J. Shawe-Taylor, PAC-Bayes analysis beyond the usual bounds. NeurIPS 2020. PDF
  • O. Rivasplata, E. Parrado-Hernández, J. Shawe-Taylor, S. Sun, Cs. Szepesvári, PAC-Bayes bounds for stable algorithms with instance-dependent priors. NeurIPS 2018. PDF
  • A.E. Litvak, O. Rivasplata, Smallest singular value of sparse random matrices. Studia Math., 212, 3 (2012), 195-218. PDF
  • O. Rivasplata, J. Rychtar, B. Schmuland, Reversibility for diffusions via quasi-invariance. Acta Univ. Carolin. Math. Phys., 48, 1 (2007), 3-10. PDF
  • O. Rivasplata, J. Rychtar, C. Sykes, Evolutionary games in finite populations. Pro Mathematica, 20, 39/40 (2006), 147-164. PDF
  • O. Rivasplata, B. Schmuland, Invariant and reversible measures for random walks on Z. Pro Mathematica, 19, 37/38 (2005), 117-124. PDF

Workshop Papers

Expository Notes
  • O. Rivasplata, A note on a confidence bound of Kuzborskij and Szepesvári. (2021) PDF
  • O. Rivasplata, Subgaussian random variables: An expository note. (2012) PDF

Utterly arXiv'ed
  • O. Rivasplata, V. Tankasali, Cs. Szepesvári, PAC-Bayes with Backprop. (2019) PDF



Machine Learning Links
What is machine learning?
Understanding Machine Learning
Rich Sutton's incomplete ideas (and RL resources)
Robert Duin's 37 steps (and PR tools and blog)
Advice for Machine Learning students

Math Links
What's new (Terry Tao's blog)
Maths Research Seminars (beta).
The complex number operations neatly visualised.
Advice for Math students

Probability Links (probably accessible)
Almost Sure
Research in Probability
The Gaussian Processes Website
Advice for Probability students

Stats Links (most significant)
Random stuff
Frequentism and Bayesianism
Advice for Stats students

Writing aids
How to Write Mathematics, tips from the Mathematics Student Handbook at Trent University.
A Guide to Writing Mathematics by Kevin Lee.
Writing Mathematics by Berry & Lawson.
The Underground Grammarian by Richard Mitchell.

Canadian Links Yay Canada
My Canadian home town is Edmonton, Alberta.
Not far from the beautiful Canadian Rocky Mountains.
Favourite spots in the Canadian Rockies are Jasper, Banff, Lake Louise, Emerald Lake.
Datasets CIFAR-10 and CIFAR-100 are named after the Canadian Institute For Advanced Research.

Peruvian Links Yay Canada
My birth town is Trujillo, the marinera dance town.
Sometimes people ask me about Machu Picchu, it's a great place to see.
They ask me less about Arequipa though it is also a great place to visit.
Last link, in case you care to know, is about Pisco.