Z Yuan, Y Yan, M Sonka… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Abstract Deep AUC Maximization (DAM) is a new paradigm for learning a deep neural network by maximizing the AUC score of the model on a dataset. Most previous works of …
J Yang, N Kiyavash, N He - Advances in Neural Information …, 2020 - proceedings.neurips.cc
Nonconvex minimax problems appear frequently in emerging machine learning applications, such as generative adversarial networks and adversarial learning. Simple …
Gradient descent ascent (GDA), the simplest single-loop algorithm for nonconvex minimax optimization, is widely used in practical applications such as generative adversarial …
Areas under ROC (AUROC) and precision-recall curves (AUPRC) are common metrics for evaluating classification performance for imbalanced problems. Compared with AUROC …
F Huang, X Wu, H Huang - Advances in Neural Information …, 2021 - proceedings.neurips.cc
In the paper, we propose a class of efficient mirror descent ascent methods to solve the nonsmooth nonconvex-strongly-concave minimax problems by using dynamic mirror …
P Mahdavinia, Y Deng, H Li… - Advances in Neural …, 2022 - proceedings.neurips.cc
Despite the established convergence theory of Optimistic Gradient Descent Ascent (OGDA) and Extragradient (EG) methods for the convex-concave minimax problems, little is known …
L Chen, B Yao, L Luo - Advances in Neural Information …, 2022 - proceedings.neurips.cc
This paper considers stochastic first-order algorithms for minimax optimization under Polyak- {\L} ojasiewicz (PL) conditions. We propose SPIDER-GDA for solving the finite-sum problem …
G Carloni, E Pachetti… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In this paper, we present a novel method for the automatic classification of medical images that learns and leverages weak causal signals in the image. Our framework consists of a …
T Yang - arXiv preprint arXiv:2206.00439, 2022 - arxiv.org
X-risk is a term introduced to represent a family of compositional measures or objectives, in which each data point is compared with a large number of items explicitly or implicitly for …