Adversarial training methods typically align distributions by solving
tw...
We present MLRG Deep Curvature suite, a PyTorch-based, open-source packa...
Bayesian inference was once a gold standard for learning with neural
net...
We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose
...
Deep neural networks are typically trained by optimizing a loss function...
The loss functions of deep neural networks are complex and their geometr...
In industrial machine learning pipelines, data often arrive in parts.
Pa...