76 citations · 168 across the 6 of their papers we have counts for
Showing 2018Show all
2 papers · 1 filter
cs.LG2018
Spurious samples in deep generative models: bug or feature?
Balázs Kégl, Mehdi Cherti, Akın Kazakçı
Traditional wisdom in generative modeling literature is that spurious samples that a model can generate are errors and they should be avoided. Recent research, however, has shown i…
cs.LG2018
Similarity encoding for learning with dirty categorical variables
Patricio Cerda, Gaël Varoquaux, Balázs Kégl
For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. "Dirt…