Course curriculum

Much as replacing hand-designed features with learned functions has revolutionized how we solve perceptual tasks, learned algorithms also have the potential to transform how we train machine learning models. Learned optimizers are one such learned algorithm. Instead of writing down mathematical expressions to perform optimization, a learned optimizer learns the function to perform optimization. This talk will outline how these learned optimizers work, and discuss a number of difficulties that arise when training them. Finally I will share some interesting behaviours which are starting to emerge.

  • 1

    Learned Optimisers: Learning to Learn Optimisation Algorithms

    • Learned Optimisers: Learning to Learn Optimisation Algorithms


Research Scientist Google Brain

Luke Metz

Luke Metz is a research scientist at Google Brain working on meta-learning and learned optimisers. He's interested in building general purpose, learned learning algorithms that not only perform well, but generalises to new types of never before seen problems.


Don't miss a chance to be among FIRST 100 to register for APAC 2022