Robust Learning-Augmented Dictionaries

Authors: Ali Zeynali, Shahin Kamali, Mohammad Hajiesmaili

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments show that Robust SL outperforms alternative data structures using both synthetic and real datasets.
Researcher Affiliation Academia 1Manning College of Information & Computer Sciences, University of Massachusetts Amherst, USA 2Department of Electrical Engineering & Computer Science, York University, Canada .
Pseudocode No The paper describes the algorithm's details in prose (e.g., "Algorithmic details of Robust SL.") but does not include a structured pseudocode or algorithm block.
Open Source Code No The paper does not provide an explicit statement about releasing its source code or a direct link to a code repository for the methodology described.
Open Datasets Yes BBC news article dataset. We also use the BBC news article dataset (Kushwaha, 2023) to evaluate the performance of Robust SL and other baseline data structures in responding to news article queries (Chen et al., 2022; Kostakos, 2020). In these experiments, we select a fraction of the entire dataset to predict item frequencies (training dataset) in the remaining portion (test dataset)." and "Kushwaha, S. BBCFull Text Document Classification. https://www.kaggle. com/datasets/shivamkushwaha/ bbc-full-text-document-classification, 2023. Accessed: 2023-05-17.
Dataset Splits No The paper mentions splitting data into training and test sets (e.g., "randomly select 40% of the entire data as the training dataset, 25% (of the training dataset) as the size of the adversary dataset," and "training dataset in the remaining portion (test dataset)"). However, it does not explicitly provide details for a separate validation set split.
Hardware Specification No The paper does not explicitly describe the hardware (e.g., specific GPU/CPU models or cloud resources) used to run its experiments.
Software Dependencies No The paper does not provide a reproducible description of ancillary software with specific version numbers.
Experiment Setup Yes We select θ = 0.05 in Robust SL for our experiments... In addition, we select p = 0.368... Randomly select 40% of the entire data as the training dataset, 25% (of the training dataset) as the size of the adversary dataset, θ = 0.05, and p = 0.368 (as used in synthetic experiments)...