Gradient clipping is an important technique for deep neural networks wit...
When users move in a physical space (e.g., an urban space), they would h...
As a prevalent distributed learning paradigm, Federated Learning (FL) tr...
Bilevel optimization has arisen as a powerful tool for solving a variety...
In distributed training of deep neural networks or Federated Learning (F...
Large-scale distributed training of deep acoustic models plays an import...
In this paper, we study distributed algorithms for large-scale AUC
maxim...
Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchr...
The traditional game of cops and robbers is played on undirected graph.
...
Adaptive gradient algorithms perform gradient-based updates using the hi...
Generative Adversarial Networks (GANs) are powerful class of generative
...
Current deep neural networks can achieve remarkable performance on a sin...
In the game of Cops and Robber, a team of cops attempts to capture a rob...
Stochastic AUC maximization has garnered an increasing interest due to b...
In this paper, we consider first-order algorithms for solving a class of...
Min-max saddle-point problems have broad applications in many tasks in
m...
Error bound conditions (EBC) are properties that characterize the growth...
In this paper, we study stochastic non-convex optimization with non-conv...
The Hessian-vector product has been utilized to find a second-order
stat...