In recent years, convolutional neural networks (CNNs) have shown great performance in
various fields such as image classification, pattern recognition, and multi-media …

Support vector machine (SVM) is an optimal margin based classification technique in
machine learning. SVM is a binary linear classifier which has been extended to non-linear …

Machine learning develops rapidly, which has made many theoretical breakthroughs and is
widely applied in various fields. Optimization, as an important part of machine learning, has …

Training large neural networks requires distributing learning across multiple workers, where
the cost of communicating gradients can be a significant bottleneck. signSGD alleviates this …

We introduce a new and increasingly relevant setting for distributed optimization in machine
learning, where the data defining the optimization are unevenly distributed over an …

This paper contributes improvements on both the effectiveness and efficiency of Matrix
Factorization (MF) methods for implicit feedback. We highlight two critical issues of existing …

In 1963, Polyak proposed a simple condition that is sufficient to show a global linear
convergence rate for gradient descent. This condition is a special case of the Łojasiewicz …

It is well understood that client-master communication can be a primary bottleneck in
Federated Learning. In this work, we address this issue with a novel client subsampling …

Coordinate descent algorithms solve optimization problems by successively performing
approximate minimization along coordinate directions or coordinate hyperplanes. They have …

Traditional analyses in non-convex optimization typically rely on the smoothness
assumption, namely requiring the gradients to be Lipschitz. However, recent evidence …