Abstract: Knowledge distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits or ...

Abstract: Most of the existing Out-Of-Distribution (OOD) detection algorithms depend on single input source: the feature, the logit, or the softmax probability. However, the immense diversity of the ...

All datasets used in the paper are available in the data folder. For example, to run the experiments on one of the the synthetic binary datasets with ER graph, 10 nodes edge ratio 2, and 1000 samples, ...

Dataset distillation reduces the network training cost by synthesizing small and informative datasets from largescale ones. Despite the success of the recent dataset distillation algorithms, three ...

We develop a generalized hybrid approach that incorporates ACET/logit and Ricardian to account for both conversion cost and comparative advantage. We use this hybrid approach to estimate future ...