.
This is a *legacy* sort of page.
Belonging to Omar Rivasplata (link directs to current page).
The original page was hosted in UCL Statistical Science servers.
I no longer have access to said servers and so this page is no longer updated.
Below is the content of the said page (minus outdated links).
Data, Environments, and Learners: Theory and Algorithms
Research Group at UCL Statistical Science
Led by Omar Rivasplata
IMSS Fellow
|
Top-level areas of interest
|
| AI. Machine Learning. Statistical Learning Theory. Mathematics. Probability and Statistics.
|
| What is this research group about? |
The group's mission is solving optimisation and certification problems for 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) we are interested in deep learning algorithms which are highly relevant nowadays since neural networks are important components of many modern algorithmic learning systems.
Our approach consists of leveraging mathematics, statistics, and computer experiments, to obtain meaningful knowledge about these algorithms and to inform better design choices. Particulary, we aim to develop learning and certification strategies that make efficient use of the available data and deliver reliable performance guarantees.
|
Please reach out to the group lead to enquire.
|
-
Luo Zhen, MSc Data Science (Summer 2023).
-
Sharmilan Ilankesan, MSc Statistical Science (Summer 2023).
-
Carlos Pita Amerigo, MSc Mathematics (2022/23).
-
Qinyi Wu, MSc Mathematics (2022/23).
-
Yousef Nami, MSc Computational Statistics and Machine Learning (Summer 2022).
-
Qingyu Feng, MSc Computational Statistics and Machine Learning (Summer 2022).
Please reach out to the group lead to enquire.
|
| Probability Links (probably accessible) |
| Stats Links (most significant) |
|
|