Data Augmentation via Levy Processes
By Stefan Wager, William Fithian, Percy Liang. 2016
5 citations recorded by the source corpus.
If a document is about travel, we may expect that short snippets of the document should also be about travel. We introduce a general framework for incorporating these types of invariances into a discriminative classifier. The framework imagines data as being drawn from a slice of a Levy process. If we slice the Levy process at an earlier point in time, we obtain additional pseudo-examples, which can be used to train the classifier. We show that this scheme has two desirable properties: it preserves the Bayes decision boundary, and it is equivalent to fitting a generative model in the limit where we rewind time back to 0. Our construction captures popular schemes such as Gaussian feature noising and dropout training, as well as admitting new generalizations.
Subfields: Artificial Intelligence, Mathematical Physics, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Dan Jurafsky
- Percy Liang
- Jiwei Li
- Mohit Bansal
- Kyunghyun Cho
- Jianfeng Gao
- Yonatan Belinkov
- Christopher D. Manning
In Mathematical Physics
In Molecular Biology
Citations in the corpus
- Data Noising as Smoothing in Neural Network Language Models (2017, background): “Additionally, Wager et al. (2014) show that noising can inject appropriate generative assumptions into discriminative models to reduce their generalization error, but do not consider sequence models (Wager et al., 2016).”