An Exponential Tail Bound for the Deleted Estimate

Authors: Karim Abou–Moustafa, Csaba Szepesvári3143-3150

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Using recent advances in concentration inequalities, and using a notion of stability that is weaker than uniform stability but distribution dependent and amenable to computation, we derive an exponential tail bound for the concentration of the estimated risk of a hypothesis returned by a general learning rule, where the estimated risk is expressed in terms of the deleted estimate.
Researcher Affiliation Collaboration Dept. of Computing Sciecne, University of Alberta Edmonton, Alberta T6G 2E8, Canada aboumous@ualberta.ca, szepesva@ualberta.ca Currently with SAS Inst. Inc., Cary, North Carolina, USA Currently with Google Deep Mind, London, UK
Pseudocode No The paper is theoretical and mathematical, and it does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not mention providing any open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not use or mention any specific datasets for empirical evaluation.
Dataset Splits No The paper is theoretical and does not involve training, validation, or test data splits for experiments.
Hardware Specification No The paper is theoretical and does not mention any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training settings.