Ross Clarke
Ross received the BA and MEng degrees in Engineering from the University of Cambridge, specialising in Information and Computer Engineering. His Part IIB Project, Parallelising Sequential Monte Carlo, was completed under the supervision of Dr Sumeetpal Singh in the Signal Processing and Communications Lab. He joined the Machine Learning Group as a PhD student in 2018, and is supervised by Dr José Miguel Hernández-Lobato under funding from EPSR
Publications
Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation
Ross M. Clarke, Elre T. Oldewage, José Miguel Hernández-Lobato, April 2022. (In 10th International Conference on Learning Representations). Virtual.
Abstract▼ URL
Machine learning training methods depend plentifully and intricately on hyperparameters, motivating automated strategies for their optimisation. Many existing algorithms restart training for each new hyperparameter choice, at considerable computational cost. Some hypergradient- based one-pass methods exist, but these either cannot be applied to arbitrary optimiser hyperparameters (such as learning rates and momenta) or take several times longer to train than their base models. We extend these existing methods to develop an approximate hypergradient-based hyperparameter optimiser which is applicable to any continuous hyperparameter appearing in a differentiable model weight update, yet requires only one training episode, with no restarts. We also provide a motivating argument for convergence to the true hypergradient, and perform tractable gradient-based optimisation of independent learning rates for each model parameter. Our method performs competitively from varied random hyperparameter initialisations on several UCI datasets and Fashion-MNIST (using a one-layer MLP), Penn Treebank (using an LSTM) and CIFAR-10 (using a ResNet-18), in time only 2-3x greater than vanilla training.