Deep Learning
Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations
Each attribute combination, called an'arm', is associated with a Beta density from which the service's accuracy is sampled. We expect the GP to smooth the parameters of the Beta density over related arms to mitigate sparsity.
Aligning Pretraining for Detection via Object-Level Contrastive Learning Fangyun Wei Yue Gao
Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream task.
Why Normalizing Flows Fail to Detect Out-of-Distribution Data
We identify mechanisms through which normalizing flows can simultaneously increase likelihood for all structured images.
Suplement Material: Generalization Error Bounds on Deep Learning with Markov Datasets Lan V. Truong Department of Engineering University of Cambridge Cambridge, CB2 1PZ lt407@cam.ac.uk
Here, w will be called the vector of weights of the neuron.
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
We then use these approximate subclass labels as a form of noisy supervision in a distributionally robust optimization objective.