Search Results for author:
Found 4 papers, 3 papers with code
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).
Discount Factor as a Regularizer in Reinforcement Learning
Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor.
Lifelong Learning by Adjusting Priors
We develop a framework for lifelong learning in deep neural networks that is based on generalization bounds, developed within the PAC-Bayes framework.
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
