A Vector Bernstein Inequality for Self-Normalized Martingales

Authors: Ingvar Ziemann

TMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove a Bernstein inequality for vector-valued self-normalized martingales. We first give an alternative perspective of the corresponding sub-Gaussian bound due to Abbasi Yadkori et al. (2011) via a PAC-Bayesian argument with Gaussian priors. By instantiating this argument to priors drawn uniformly over well-chosen ellipsoids, we obtain a Bernstein bound.
Researcher Affiliation Academia Ingvar Ziemann EMAIL University of Pennsylvania
Pseudocode No The paper focuses on mathematical proofs and theoretical derivations and does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements about releasing source code, nor does it provide links to any code repositories for the methodology described.
Open Datasets No The paper is theoretical, presenting mathematical proofs and inequalities. It does not describe or use any specific datasets for empirical evaluation, hence no information about public or open datasets is provided.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with datasets, thus no information regarding dataset splits (training, validation, test) is provided.
Hardware Specification No The paper presents theoretical work on a vector Bernstein inequality and does not describe any computational experiments that would require hardware specifications.
Software Dependencies No The paper is purely theoretical, focusing on mathematical derivations and proofs. It does not mention any software or libraries with version numbers used for experimental purposes.
Experiment Setup No The paper is purely theoretical, focusing on mathematical derivations and proofs. It does not describe any experimental setup details, hyperparameters, or training configurations.