PAC-Bayes Learning Bounds for Sample-Dependent Priors

Authors: Pranjal Awasthi, Satyen Kale, Stefani Karp, Mehryar Mohri

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We present a series of new PAC-Bayes learning guarantees for randomized algorithms with sample-dependent priors. Our most general bounds make no assumption on the priors and are given in terms of certain covering numbers under the infinite-Rényi divergence and the ℓ1 distance. We show how to use these general bounds to derive learning bounds in the setting where the sample-dependent priors obey an infinite-Rényi divergence or ℓ1-distance sensitivity condition. We also provide a flexible framework for computing PAC-Bayes bounds, under certain stability assumptions on the sample-dependent priors, and show how to use this framework to give more refined bounds when the priors satisfy an infinite-Rényi divergence sensitivity condition.
Researcher Affiliation Collaboration Pranjal Awasthi Google Research and Rutgers University pranjalawasthi@google.com Satyen Kale Google Research satyenkale@google.com Stefani Karp Google Research and Carnegie Mellon University stefanik@google.com Mehryar Mohri Google Research and Courant Institute of Mathematical Sciences mohri@google.com
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper is theoretical and does not mention any datasets used for training or public availability of such datasets.
Dataset Splits No The paper is theoretical and does not describe any dataset splits (training, validation, test).
Hardware Specification No The paper is theoretical and does not describe hardware used, as it does not conduct experiments.
Software Dependencies No The paper is theoretical and does not mention specific software dependencies with version numbers, as it does not conduct experiments.
Experiment Setup No The paper is theoretical and does not provide details about an experimental setup, as it does not conduct experiments.