Efficient Data-Dependent Learnability
arXiv:2011.10334
Abstract
The predictive normalized maximum likelihood (pNML) approach has recently been proposed as the min-max optimal solution to the batch learning problem where both the training set and the test data feature are individuals, known sequences. This approach has yields a learnability measure that can also be interpreted as a stability measure. This measure has shown some potential in detecting out-of-distribution examples, yet it has considerable computational costs. In this project, we propose and analyze an approximation of the pNML, which is based on influence functions. Combining both theoretical analysis and experiments, we show that when applied to neural networks, this approximation can detect out-of-distribution examples effectively. We also compare its performance to that achieved by conducting a single gradient step for each possible label.
arXiv comment12 pages, 10 figures
References in corpus (5)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Understanding Black-box Predictions via Influence Functions
- Understanding deep learning requires rethinking generalization
- A New Look at an Old Problem: A Universal Learning Approach to Linear Regression
- Deep pNML: Predictive Normalized Maximum Likelihood for Deep Neural Networks