Baruch Epstein
Research Subjects
Research Interests
Baruch Epstein has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Ron Amit
The Viterbi Faculty of Electrical Engineering Technion -Israel Institute of Technology Haifa Israel
1 shared publication Ron Meir
Technion - Israel institute of Technology
1 shared publication- Ron Meir
Technion -Israel Institute of Technology Haifa Israel
1 shared publication - Shay Moran
Technion, Haifa, Israel
1 shared publication Tomer Michaeli
Technion - Israel institute of Technology
1 shared publication
Latest Publications
- Open Access
Integral Probability Metrics PAC-Bayes Bounds
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 this bound with the IPM being the total variation metric and the Wasserstein distance. A notable feature of the obtained bounds is that they naturally interpolate between classical uniform convergence bounds in the worst case (when the prior and posterior are far away from each other), and improved bounds in favorable cases (when the posterior and prior are close). This illustrates the possibility of reinforcing classical generalization bounds with algorithm- and data-dependent components, thus making them more suitable to analyze algorithms that use a large hypothesis space.
Open AccessIntegral Probability Metrics PAC-Bayes Bounds
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 this bound with the IPM being the total variation metric and the Wasserstein distance. A notable feature of the obtained bounds is that they naturally interpolate between classical uniform convergence bounds in the worst case (when the prior and posterior are far away from each other), and improved bounds in favorable cases (when the posterior and prior are close). This illustrates the possibility of reinforcing classical generalization bounds with algorithm- and data-dependent components, thus making them more suitable to analyze algorithms that use a large hypothesis space.
- Open Access
- 18 January 2019
- Published by Springer Nature
- p. 494-509
Joint Autoencoders: A Flexible Meta-learning Framework
- 18 January 2019
- Published by Springer Nature
- p. 494-509
Open AccessJoint Autoencoders: A Flexible Meta-learning Framework