Information-theoretic analysis of generalization capability of learning algorithms

Authors: Aolin Xu, Maxim Raginsky

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We derive upper bounds on the generalization error of a learning algorithm in terms of the mutual information between its input and output. The bounds provide an information-theoretic understanding of generalization in learning problems, and give theoretical guidelines for striking the right balance between data fit and generalization by controlling the input-output mutual information.
Researcher Affiliation Academia Department of Electrical and Computer Engineering and Coordinated Science Laboratory, University of Illinois, Urbana, IL 61801, USA.
Pseudocode No The paper describes algorithms such as the Gibbs algorithm and noisy ERM, but does not provide any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not mention or provide access to any open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not conduct experiments with specific datasets, thus no information on training data availability is provided.
Dataset Splits No The paper is theoretical and does not describe experimental validation, so no dataset split information (training, validation, test) is provided.
Hardware Specification No The paper is theoretical and does not describe any experimental setup or the hardware used for computations.
Software Dependencies No The paper is theoretical and does not describe any experimental setup or software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not detail any experimental setup, hyperparameters, or training configurations.