CaltechAUTHORS
  A Caltech Library Service

NAOMI: Non-Autoregressive Multiresolution Sequence Imputation

Liu, Yukai and Yu, Rose and Zheng, Stephan and Zhan, Eric and Yue, Yisong (2019) NAOMI: Non-Autoregressive Multiresolution Sequence Imputation. . (Submitted) https://resolver.caltech.edu/CaltechAUTHORS:20190205-100357088

[img] PDF - Submitted Version
See Usage Policy.

6Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190205-100357088

Abstract

Missing value imputation is a fundamental problem in modeling spatiotemporal sequences, from motion tracking to the dynamics of physical systems. In this paper, we take a non-autoregressive approach and propose a novel deep generative model: Non-AutOregressive Multiresolution Imputation (NAOMI) for imputing long-range spatiotemporal sequences given arbitrary missing patterns. In particular, NAOMI exploits the multiresolution structure of spatiotemporal data to interpolate recursively from coarse to fine-grained resolutions. We further enhance our model with adversarial training using an imitation learning objective. When trained on billiards and basketball trajectories, NAOMI demonstrates significant improvement in imputation accuracy (reducing average prediction error by 60% compared to autoregressive counterparts) and generalization capability for long range trajectories in systems of both deterministic and stochastic dynamics.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
https://arxiv.org/abs/1901.10946arXivDiscussion Paper
Record Number:CaltechAUTHORS:20190205-100357088
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190205-100357088
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:92657
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:05 Feb 2019 18:11
Last Modified:03 Oct 2019 20:46

Repository Staff Only: item control page