65 citations · 115 across the 15 of their papers we have counts for
3 papers · 1 filter
Exploiting weight-space symmetries for approximating curvature
Artem Artemev, Rui Xia, Benjamin M. Boyd +4
Many machine learning techniques rely on approximating a loss function's curvature, but this is notoriously hard to do at the scale of modern deep networks. Surprisingly, no previo…
Recommendations for Baselines and Benchmarking Approximate Gaussian Processes
Sebastian W. Ober, Artem Artemev, Marcel Wagenländer +2
Gaussian processes (GPs) are a mature and widely-used component of the ML toolbox. One of their desirable qualities is automatic hyperparameter selection, which allows for training…
Memory Safe Computations with XLA Compiler
Artem Artemev, Tilman Roeder, Mark van der Wilk
Software packages like TensorFlow and PyTorch are designed to support linear algebra operations, and their speed and usability determine their success. However, by prioritising spe…