Generative Modeling of Complex Data — mentioned by maximeago

Wed, 16 Mar 2022 15:33:04 GMT

We developed our own generative model for synthetic data generation. It is an autoregressive model where each variable/attribute is derived from previously generated ones using Transformers networks (more details there: https://arxiv.org/pdf/2202.02145.pdf). So yes, correlations are modelled, although exact multicollinearity (when there is a linear relationship between bunch of attributes) would be a bit blurry in the synthetic data. This being said, the goal of Sarus is to enable analysis on the original data with privacy guarantee on the result (synthetic data is merely used as a tool and a…

Paper and discussion history. A mention is not an endorsement.

Generative Modeling of Complex Data — mentioned by maximeago

Wed, 16 Mar 2022 14:59:54 GMT

We developed our own generative model for synthetic data generation. It is an autoregressive model where each variable is derived from previously generated ones using Transformers networks. If you are interested, you have more details in: https://arxiv.org/pdf/2202.02145.pdf When we say it works on any types of data, we mean: numerical, categorical, text, images and compositions of those types (see the paper).

Paper and discussion history. A mention is not an endorsement.

Generative Modeling of Complex Data · HackerPapers discussions

Generative Modeling of Complex Data — mentioned by maximeago

Generative Modeling of Complex Data — mentioned by maximeago