5 papers
Spectral Adversarial MixUp for Few-Shot Unsupervised Domain Adaptation
Jiajin Zhang, Hanqing Chao, Amit Dhurandhar +4
Domain shift is a common problem in clinical applications, where the training images (source domain) and the test images (target domain) are under different distributions. Unsuperv…
Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization
Xuan Zhang, Gabriel Mancino-Ball, Necdet Serhat Aybat +1
We propose a novel single-loop decentralized algorithm called DGDA-VR for solving the stochastic nonconvex strongly-concave minimax problem over a connected network of agents.…
Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data
Yonggui Yan, Jie Chen, Pin-Yu Chen +3
We first propose a decentralized proximal stochastic gradient tracking method (DProxSGT) for nonconvex stochastic composite problems, with data heterogeneously distributed on multi…
Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization
Zichong Li, Pin-Yu Chen, Sijia Liu +2
Many real-world problems not only have complicated nonconvex functional constraints but also use a large number of data points. This motivates the design of efficient stochastic me…
When Neural Networks Fail to Generalize? A Model Sensitivity Perspective
Jiajin Zhang, Hanqing Chao, Amit Dhurandhar +4
Domain generalization (DG) aims to train a model to perform well in unseen domains under different distributions. This paper considers a more realistic yet more challenging scenari…