Stable Rank
Stable rank, a concept related to the effective dimensionality of data or model parameters, is central to various machine learning tasks, primarily aiming to improve efficiency and robustness of ranking algorithms. Current research focuses on applying stable rank concepts within diverse areas, including learning to rank for information retrieval, speech model evaluation, and active learning, often employing techniques like gradient boosted trees, neural networks, and variational autoencoders. These advancements offer improved performance and interpretability in ranking systems across numerous applications, from search engines and recommender systems to biomedical named entity recognition and even chiplet placement optimization in hardware design.
Papers
Adversarial Attacks on Online Learning to Rank with Click Feedback
Jinhang Zuo, Zhiyao Zhang, Zhiyong Wang, Shuai Li, Mohammad Hajiesmaili, Adam Wierman
RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank
Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Kai Chen, Rui Yan