Data, Environments, and Learners: Theory and Algorithms

Research Group at UCL Statistical Science

Led by Omar Rivasplata

IMSS Fellow

Top-level areas of interest
Algorithmic Learning Theory.   Machine Learning Theory and Practice.   Probability and Statistics.  

What is this research group about?
The group's mission is producing meaningful knowledge about machine learning algorithms.

We are interested in sound theory that helps to understand the performance (optimisation, generalisation) of machine learning algorithms, most notably (but not only) deep learning algorithms which are highly relevant nowadays since neural networks are important components of many modern algorithmic learning systems, aka AI.

We also aim to develop learning and certification strategies that are inspired by sound principles and make efficient use of the available data.

Current topic(s) of focus
PAC-Bayes bounds.   Self-certified learning.   Conformal Prediction.

How to get involved
Please reach out to the group lead.


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.