The collective opion of a crowd is often considered to be better than that of a single expert. In this talk, we present some results that exploit this old idea in two machine learning problems: ensemble learning and multi-modal imitation learning.

Ensemble learning aims to find a collection of models with each having a different "opinion/view" on data, then combine them for prediction. We show that linear combinations can fail to generalize, while convex combinations can generalise for a broad class of Lipschitz-continuous loss functions. In addition, considering that there is little empirical study on learning a convex combination, we perform extensive experiments to study various greedy learning algorithms adapted for learning a convex combination. Our results suggest that a greedy algorithm based on a variant of the recently reinvogorated Frank-Wolfe algorithm achieves good performance without much hyperparameter tuning.

Multi-modal imitation learning aims to learn how to complete a task from demonstrations by possibly multiple experts. While some demonstration data consists of multiple behavior modes, typical approaches often learn a single behavior mode. We extend the maximum entropy inverse reinforcement learning framework to handle multi-modal data, and demonstrate its effectiveness on a multi-modal taxi-driving dataset.

About Maths Colloquium

The Mathematics Colloquium is directed at students and academics working in the fields of pure and applied mathematics, and statistics. 

We aim to present expository lectures that appeal to our wide audience.

Information for speakers

Information for speakers

Maths colloquia are usually held on Mondays, from 2pm to 3pm, in various locations at St Lucia.

Presentations are 50 minutes, plus five minutes for questions and discussion.

Available facilities include:

  • computer 
  • data projector
  • chalkboard or whiteboard

To avoid technical difficulties on the day, please contact us in advance of your presentation to discuss your requirements.


Parnell #07