A Decision Tree Framework for Spatiotemporal Sequence Prediction
Abstract
We study the problem of learning to predict a spatiotemporal output sequence given an input sequence. In contrast to conventional sequence prediction problems such as part-of-speech tagging (where output sequences are selected using a relatively small set of discrete labels), our goal is to predict sequences that lie within a high-dimensional continuous output space. We present a decision tree framework for learning an accurate non-parametric spatiotemporal sequence predictor. Our approach enjoys several attractive properties, including ease of training, fast performance at test time, and the ability to robustly tolerate corrupted training data using a novel latent variable approach. We evaluate on several datasets, and demonstrate substantial improvements over existing decision tree based sequence learning frameworks such as SEARN and DAgger.
Additional Information
© 2015 ACM.Additional details
- Eprint ID
- 60579
- DOI
- 10.1145/2783258.2783356
- Resolver ID
- CaltechAUTHORS:20150928-132143651
- Created
-
2015-09-29Created from EPrint's datestamp field
- Updated
-
2021-11-10Created from EPrint's last_modified field