MA333      Half Unit
Optimisation for Machine Learning

This information is for the 2021/22 session.

Teacher responsible

Prof Laszlo Vegh COL 2.02


This course is available on the BSc in Business Mathematics and Statistics, BSc in Mathematics and Economics, BSc in Mathematics with Economics and BSc in Mathematics, Statistics and Business. This course is available as an outside option to students on other programmes where regulations permit. This course is available with permission to General Course students.


Students must have a knowledge of continuous optimisation to the level of 'Optimisation Theory (MA208)'.

Course content

Machine learning uses tools from statistics, mathematics, and computer science for a broad range of problems in data analytics. The course introduces a range of optimisation methods that play fundamental roles in machine learning. This is a proof-based course that focuses on the underlying mathematical models and concepts.

Basic tools from convex analysis. First-order methods and convergence guarantees, including conditional gradient descent, stochastic gradient descent. Online convex optimization, online gradient and multiplicative weight methods. Second-order optimization, Newton’s method, quasi-Newton methods. Interior-point methods. Quadratic programming, support vector machines. Fundamental concepts in neural networks. Reinforcement learning, multi-armed bandit problems.


This course is delivered through a combination of classes and lectures totalling a minimum of 32 hours across Lent and Summer term. This year, apart from pre-recorded lecture videos, there will be a weekly live online session of an hour. Depending on circumstances, classes might be online.

Formative coursework

Students will be expected to produce 8 exercises in the LT.

Written answers to set problems will be expected on a weekly basis.

Indicative reading

  • Boyd, S., & Vandenberghe, L. (2004). Convex optimization. Cambridge University Press.
  • Shalev-Shwartz, S. & Ben-David, S. (2004). Understanding Machine Learning: From Theory to Algorithms. . Cambridge University Press.
  • Nesterov, Y. (2018). Lectures on convex optimization (Vol. 137). Springer.
  • Blum, A., Hopcroft, J., & Kannan, R. (2020). Foundations of data science. Cambridge University Press.
  • Vishnoi, N. (2018). Algorithms for Convex Optimization (2021). Cambridge University Press.


Exam (90%, duration: 2 hours) in the summer exam period.
Coursework (10%) in the LT.

The coursework will comprise two problem sets during term time.

Course selection videos

Some departments have produced short videos to introduce their courses. Please refer to the course selection videos index page for further information.

Important information in response to COVID-19

Please note that during 2021/22 academic year some variation to teaching and learning activities may be required to respond to changes in public health advice and/or to account for the differing needs of students in attendance on campus and those who might be studying online. For example, this may involve changes to the mode of teaching delivery and/or the format or weighting of assessments. Changes will only be made if required and students will be notified about any changes to teaching or assessment plans at the earliest opportunity.

Key facts

Department: Mathematics

Total students 2020/21: Unavailable

Average class size 2020/21: Unavailable

Capped 2020/21: No

Value: Half Unit

Guidelines for interpreting course guide information

Personal development skills

  • Self-management
  • Problem solving
  • Application of information skills
  • Application of numeracy skills
  • Specialist skills