Generalization Bounds with Minimal Dependency on Hypothesis Class via Distributionally Robust Optimization

no code implementations • 21 Jun 2021 • Yibo Zeng, Henry Lam

In contrast to the hypothesis class complexity in ERM, our DRO bounds depend on the ambiguity set geometry and its compatibility with the true loss function.

BIG-bench Machine Learning Generalization Bounds

AsyncQVI: Asynchronous-Parallel Q-Value Iteration for Discounted Markov Decision Processes with Near-Optimal Sample Complexity

1 code implementation • 3 Dec 2018 • Yibo Zeng, Fei Feng, Wotao Yin

In this paper, we propose AsyncQVI, an asynchronous-parallel Q-value iteration for discounted Markov decision processes whose transition and reward can only be sampled through a generative model.