Timezone: »

 
Generating High Fidelity Synthetic Data via Coreset selection and Entropic Regularization
Omead Pooladzandi · Pasha Khosravi · Erik Nijkamp · Baharan Mirzasoleiman

Fri Dec 02 09:14 AM -- 09:16 AM (PST) @
in Synthetic Data for Empowering ML Research »
Event URL: https://openreview.net/forum?id=4mm9w-MeOjr »

Generative models have the ability to synthesize data points drawn from the data distribution, however, not all generated samples are high quality. In this paper, we propose using a combination of coresets selection methods and ``entropic regularization'' to select the highest fidelity samples. We leverage an Energy-Based Model which resembles a variational auto-encoder with an inference and generator model for which the latent prior is complexified by an energy-based model. In a semi-supervised learning scenario, we show that augmenting the labeled data-set, by adding our selected subset of samples, leads to better accuracy improvement rather than using all the synthetic samples.

Author Information

Omead Pooladzandi (University of California, Los Angeles)
Pasha Khosravi (UCLA)
Erik Nijkamp (Salesforce Research)
Baharan Mirzasoleiman (UCLA)

More from the Same Authors