While deep reinforcement learning (RL) has fueled multiple high-profile successes in machine learning, it is held back from more widespread adoption by its often poor data …
R Keisler - arXiv preprint arXiv:2202.07575, 2022 - arxiv.org
We present a data-driven approach for forecasting global weather using graph neural networks. The system learns to step forward the current 3D atmospheric state by six hours …
Structured state space sequence (S4) models have recently achieved state-of-the-art performance on long-range sequence modeling tasks. These models also have fast …
AA Team, J Bauer, K Baumli, S Baveja… - arXiv preprint arXiv …, 2023 - arxiv.org
Foundation models have shown impressive adaptation and scalability in supervised and self- supervised learning problems, but so far these successes have not fully translated to …
Tremendous progress has been made in reinforcement learning (RL) over the past decade. Most of these advancements came through the continual development of new algorithms …
Y Ding, K Yu, J Huang - Current Opinion in Structural Biology, 2023 - Elsevier
Recent advances in data science are impacting the development of classical force fields. Here we review some ideas and techniques from data science that have been used in force …
RT Lange - Proceedings of the Companion Conference on Genetic …, 2023 - dl.acm.org
The deep learning revolution has greatly been accelerated by the'hardware lottery': Recent advances in modern hardware accelerators, compilers and the availability of open-source …
B Amos - Foundations and Trends® in Machine Learning, 2023 - nowpublishers.com
Optimization is a ubiquitous modeling tool and is often deployed in settings which repeatedly solve similar instances of the same problem. Amortized optimization methods …
We explore a data-driven approach for learning to optimize neural networks. We construct a dataset of neural network checkpoints and train a generative model on the parameters. In …