Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Tifrea, Alexandru"'
Autor:
Tifrea, Alexandru, Lahoti, Preethi, Packer, Ben, Halpern, Yoni, Beirami, Ahmad, Prost, Flavien
Despite achieving promising fairness-error trade-offs, in-processing mitigation techniques for group fairness cannot be employed in numerous practical applications with limited computation resources or no access to the training pipeline of the predic
Externí odkaz:
http://arxiv.org/abs/2312.02592
It is widely believed that given the same labeling budget, active learning (AL) algorithms like margin-based active learning achieve better predictive performance than passive learning (PL), albeit at a higher computational cost. Recent empirical evi
Externí odkaz:
http://arxiv.org/abs/2212.00772
Numerous recent works show that overparameterization implicitly reduces variance for min-norm interpolators and max-margin classifiers. These findings suggest that ridge regularization has vanishing benefits in high dimensions. We challenge this narr
Externí odkaz:
http://arxiv.org/abs/2108.02883
Deep neural networks often predict samples with high confidence even when they come from unseen classes and should instead be flagged for expert evaluation. Current novelty detection algorithms cannot reliably identify such near OOD points unless the
Externí odkaz:
http://arxiv.org/abs/2012.05825
Words are not created equal. In fact, they form an aristocratic graph with a latent hierarchical structure that the next generation of unsupervised learned word embeddings should reveal. In this paper, justified by the notion of delta-hyperbolicity o
Externí odkaz:
http://arxiv.org/abs/1810.06546