← Search

Markus Meister

2 accepted papers

2021

Learning by Turning: Neural Architecture Aware Optimisation

ICML 2021spotlight

Descent methods for deep networks are notoriously capricious: they require careful tuning of step size, momentum and weight decay, and which method will work best on a new benchmark is a priori unclear. To address this problem, this paper conducts a combined study of neural architecture and optimisa…

2020

Learning compositional functions via multiplicative weight updates

NeurIPS 2020poster

Compositionality is a basic structural feature of both biological and artificial neural networks. Learning compositional functions via gradient descent incurs well known problems like vanishing and exploding gradients, making careful learning rate tuning essential for real-world applications. This p…