Recent decades have seen a rise in the use of physics methods to study different societal
phenomena. This development has been due to physicists venturing outside of their …

Averaging the parameters of models that have the same architecture and initialization can
provide a means of combining their respective capabilities. In this paper, we take the …

During typical gradient-based training of deep neural networks, all of the model's
parameters are updated at each iteration. Recent work has shown that it is possible to …

Neural networks predictions are unreliable when the input sample is out of the training
distribution or corrupted by noise. Being able to detect such failures automatically is …

Unlearning the data observed during the training of a machine learning (ML) model is an
important task that can play a pivotal role in fortifying the privacy and security of ML-based …

We show that the influence of a subset of the training samples can be removed--or"
forgotten"--from the weights of a network trained on large-scale image classification tasks …

Large machine learning models are revolutionary technologies of artificial intelligence
whose bottlenecks include huge computational expenses, power, and time used both in the …

Stochastic Gradient Descent (SGD) and its variants are mainstream methods for training
deep networks in practice. SGD is known to find a flat minimum that often generalizes well …

Inference capabilities of machine learning (ML) systems skyrocketed in recent years, now
playing a pivotal role in various aspect of society. The goal in statistical learning is to use …

Large-scale pre-trained language models have achieved impressive results on a wide
range of downstream tasks recently. However, fine-tuning an extremely large-scale pre …