Trading-Off Static and Dynamic Regret in Online Least-Squares and Beyond

Authors: Jianjun Yuan, Andrew Lamperski6712-6719

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

Reproducibility Variable Result LLM Response
Research Type Theoretical The paper focuses on theoretical contributions, providing rigorous characterizations, proving dynamic regret bounds, deriving novel step size rules, and establishing lower bounds. It includes multiple theorems (e.g., Theorem 1, 2, 3, 4, 5, 6, 7, 8) and lemmas, indicating a strong theoretical emphasis. There is no mention of empirical studies, datasets, performance metrics from experiments, or any evaluation on real-world or synthetic data.
Researcher Affiliation Academia Jianjun Yuan,1 Andrew Lamperski1 1Department of Electrical and Computer Engineering, University of Minnesota 200 Union Street SE, 4-174 Keller Hall Minneapolis, MN 55455, US {yuanx270, alampers}@umn.edu
Pseudocode Yes Algorithm 1 Discounted Online Newton Step Algorithm 2 Meta-Algorithm
Open Source Code No The paper does not include any statements about providing source code for the described methodology, nor does it provide any links to a code repository.
Open Datasets No The paper is theoretical and does not conduct empirical studies with datasets. Therefore, it does not mention or provide access information for any training datasets.
Dataset Splits No The paper is theoretical and does not conduct empirical studies with datasets. Therefore, it does not provide any training/validation/test dataset splits.
Hardware Specification No The paper is theoretical and does not discuss any empirical experiments that would require specific hardware. No hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and focuses on mathematical derivations and algorithm design. It does not mention any specific software or library versions required to replicate experiments.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training configurations.