The Science Behind Rockfish
Rockfish builds on and extends 6+ years of foundational academic research on making Deep Generative Models practical for Enterprise-scale synthetic data generation.
Since 2016, at Carnegie Mellon, co-founders Giulia Fanti and Vyas Sekar have made significant advances in the theory and practice of generative models such as developing state-of-art models for timeseries data, improving the stability and privacy of generative algorithms, practical approaches for rare sample generation, and domain-specific adaptations of deep generative models (e.g., telecommunications, IoT).
These peer-reviewed research papers have appeared at prestigious AI/ML venues such as NeuRIPS, ICML, AAAI, and domain-specific venues such as IMC, SIGCOMM.
Read more about some of these research foundations below.
Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
RareGAN: Generating Samples for
Rare Classes
Rare Classes
On the Privacy Properties of
GAN-generated Samples
GAN-generated Samples
Why Spectral Normalization Stabilizes GANs: Analysis and Improvements
Practical GAN-based Synthetic IP Header Trace Generation using NetShare