Goto

Collaborating Authors

 model metric zero-one hinge

ebea2325dc670423afe9a1f4d9d1aef5-Supplemental.pdf

  hinge cross-entropy auc zero-one 0, model metric zero-one hinge, std, (10 more...)
  Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.31)

Add feedback

A Losses Table 3 lists the losses used for training

Neural Information Processing Systems

Table 3 lists the losses used for training. T able 3: Base loss functions used for experiments. Comparison of logistic regression models trained with individual losses for the Fashion-MNIST dataset.Model / Metric Zero-one Hinge Cross-entropy AUC Zero-one 0.1603 - - - (std) ( 0 . As baselines, we train with just one loss at a time and compare the ALMO performance to this per-loss optimal performance.

  Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Regression (0.56)

Add feedback