Timezone: »

Learning to Discretize for Continuous-time Sequence Compression
Ricky T. Q. Chen · Maximilian Nickel · Matthew Le · Matthew Muckley · Karen Ullrich

Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep sequence models have costs that scale with the sequence length rather than the sequence complexity. In this work, we instead treat data sequences as observations from an underlying continuous-time process and learn how to efficiently discretize while retaining information about the full sequence. As a consequence of decoupling sequential information from its temporal discretization, our approach allows for greater compression rates and smaller computational complexity. Moreover, the continuous-time approach naturally allows us to decode at different time intervals and is amenable to randomly missing data, an important property for streaming applications. We empirically verify our approach on multiple domains involving compression of video and motion capture sequences, showing that our approaches can automatically achieve significant reductions in bit rates.

Author Information

Ricky T. Q. Chen (Facebook AI Research)
Maximilian Nickel (Meta AI)
Matthew Le (Facebook AI Research)
Matthew Muckley (Facebook AI Research)
Karen Ullrich (Facebook AI Research)

More from the Same Authors