Architectural Optimization and Feature Learning for High-Dimensional Time Series Datasets

Abstract

As our ability to sense increases, we are experiencing a transition from data-poor problems, in which the central issue is a lack of relevant data, to data-rich problems, in which the central issue is to identify a few relevant features in a sea of observations. Motivated by applications in gravitational-wave astrophysics, we study the problem of predicting the presence of transient noise artifacts in a gravitational wave detector from a rich collection of measurements from the detector and its environment. We argue that feature learning--in which relevant features are optimized from data--is critical to achieving high accuracy. We introduce models that reduce the error rate by over 60% compared to the previous state of the art, which used fixed, hand-crafted features. Feature learning is useful not only because it improves performance on prediction tasks; the results provide valuable information about patterns associated with phenomena of interest that would otherwise be undiscoverable. In our application, features found to be associated with transient noise provide diagnostic information about its origin and suggest mitigation strategies. Learning in high-dimensional settings is challenging. Through experiments with a variety of architectures, we identify two key factors in successful models: sparsity, for selecting relevant variables within the high-dimensional observations; and depth, which confers flexibility for handling complex interactions and robustness with respect to temporal variations. We illustrate their significance through systematic experiments on real detector data. Our results provide experimental corroboration of common assumptions in the machine-learning community and have direct applicability to improving our ability to sense gravitational waves, as well as to many other problem settings with similarly high-dimensional, noisy, or partly irrelevant data.

References in corpus (16)

• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• Advanced LIGO
• BayesWave: Bayesian Inference for Gravitational Wave Bursts and Instrument Glitches
• Sensitivity and Performance of the Advanced LIGO Detectors in the Third Observing Run
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• LIGO Detector Characterization in the Second and Third Observing Runs
• Machine-learning non-stationary noise out of gravitational wave detectors
• Noise Reduction in Gravitational-wave Data via Deep Learning
• Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning
• Subtracting glitches from gravitational-wave detector data during the third observing run
• Environmental Noise in Advanced LIGO Detectors
• Classification methods for noise transients in advanced gravitational-wave detectors II: performance tests on Advanced LIGO data
• Early warning of coalescing neutron-star and neutron-star-black-hole binaries from nonstationary noise background using neural networks
• Generalized Approach to Matched Filtering using Neural Networks
• Transient glitch mitigation in Advanced LIGO data with $\text{glitschen}$
• Gwadaptive_scattering: an automated pipeline for scattered light noise characterization

Cited by in corpus (1)

• Detecting and Diagnosing Terrestrial Gravitational-Wave Mimics Through Feature Learning