13 citations · 16 across the 2 of their papers we have counts for
3 papers
stat.ML2022★ 3 cited
Integral Probability Metrics PAC-Bayes Bounds
Ron Amit, Baruch Epstein, Shay Moran +1
We present a PAC-Bayes-style generalization bound which enables the replacement of the KL-divergence with a variety of Integral Probability Metrics (IPM). We provide instances of t…
stat.ML2019★ 13 cited
Generalization Bounds For Unsupervised and Semi-Supervised Learning With Autoencoders
Baruch Epstein, Ron Meir
Autoencoders are widely used for unsupervised learning and as a regularization scheme in semi-supervised learning. However, theoretical understanding of their generalization proper…
stat.ML2017
Joint auto-encoders: a flexible multi-task learning framework
Baruch Epstein, Ron Meir, Tomer Michaeli
The incorporation of prior knowledge into learning is essential in achieving good performance based on small noisy samples. Such knowledge is often incorporated through the availab…