Wednesday, May 22, 2019
2:00 PM - 3:00 PM
Cahill 312

Special TAPIR Seminar

Wasserstein Generative Adversarial Network for Time Series Data Augmentation in Astronomy
Pavlos Protopapas, Scientific Program Director and Lectur, Institute for Applied Computational Science, Harvard University,

Real-world datasets are often imbalance which is a problem for training conventional machine learning algorithms. To address the imbalance problem, many data augmentation techniques have been proposed for image recognition tasks, but only a few have been developed for time series. In this talk, I will describe a conditional Wasserstein GAN. Our model can learn the implicit probability distribution of a dataset conditioned on the irregular sampling times, amplitudes and class of the time series and generate a variety of realistic samples to complement the original dataset. We trained and evaluated our model using a pair of toy datasets and a real-world astronomical survey. We then generated realistic samples to augment the original datasets and compared the performance of a classifier trained on the GAN augmented datasets against oversampled datasets and noise-augmented datasets. The resulting generator can be used as any other generative model, allowing interpolations and extrapolations in the parameter space. [NOTE: Unusual venue]

For more information, please contact JoAnn Boyd by phone at x4280 or by email at joann@caltech.edu.