We first introduce various algorithms and techniques for machine learning and data science.
While there is a strong focus on neural network applications in unsupervised, supervised …

This paper surveys recent work in the intersection of differential privacy (DP) and fairness. It
reviews the conditions under which privacy and fairness may have aligned or contrasting …

SGD performs worse than Adam by a significant margin on Transformers, but the reason
remains unclear. In this work, we provide an explanation through the lens of Hessian:(i) …

Recent work in scientific machine learning has developed so-called physics-informed neural
network (PINN) models. The typical approach is to incorporate physical domain knowledge …

In Machine Learning, the emergence of the right to be forgotten gave birth to a paradigm
named machine unlearning, which enables data holders to proactively erase their data from …

Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed
learning with a network of clients (ie, edge devices). However, the data distribution among …

Transformer based architectures have become de-facto models used for a range of Natural
Language Processing tasks. In particular, the BERT based models achieved significant …

Abstract Model size and inference speed/power have become a major challenge in the
deployment of neural networks for many applications. A promising approach to address …

Differentiable Architecture Search (DARTS) has attracted a lot of attention due to its
simplicity and small search costs achieved by a continuous relaxation and an approximation …

Incorporating second-order curvature information into machine learning optimization
algorithms can be subtle, and doing so naïvely can lead to high per-iteration costs …