Unrolled computation graphs arise in many scenarios, including training RNNs, tuning hyperparameters through unrolled optimization, and training learned optimizers. Current …
O Bohdal, Y Yang… - Advances in neural …, 2021 - proceedings.neurips.cc
Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with …
K Frans, O Witkowski - arXiv preprint arXiv:2103.06435, 2021 - arxiv.org
Meta-learning models, or models that learn to learn, have been a long-desired target for their ability to quickly solve new tasks. Traditional meta-learning methods can require …
Machine learning algorithms and systems are progressively becoming part of our societies, leading to a growing need of building a vast multitude of accurate, reliable and interpretable …