Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers

Authors: Jeffrey Negrea, Blair Bilodeau, Nicolò Campolongo, Francesco Orabona, Dan Roy

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical If you ran experiments... (c) Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)? [N/A] All the experiments are deterministic (d) Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [N/A] All computations were done on CPU on a personal laptop computer.
Researcher Affiliation Collaboration Jeffrey Negrea University of Toronto jeffrey.negrea@mail.utoronto.ca Blair Bilodeau University of Toronto blair.bilodeau@mail.utoronto.ca Nicolò Campolongo Spanflug Technologies Gmb H nico.campolongo@spanflug.de Francesco Orabona Boston University francesco@orabona.com Daniel M. Roy University of Toronto daniel.roy@utoronto.ca
Pseudocode No The paper describes algorithms using mathematical equations and textual explanations, but it does not include a distinct 'Pseudocode' block or 'Algorithm' figure.
Open Source Code No The paper states 'All computations were done on CPU on a personal laptop computer.' and answers 'Yes' to 'Did you include the code... needed to reproduce the main experimental results', but provides no specific link or explicit statement about the open-sourcing of the described FTRL algorithm's implementation code or the root-logarithmic regularizers.
Open Datasets No The paper is theoretical and does not involve the use of specific datasets for training or evaluation. Therefore, it does not provide information about publicly available datasets.
Dataset Splits No The paper is theoretical and does not involve empirical validation on datasets, thus no dataset splits for training, validation, or testing are mentioned.
Hardware Specification No The paper states 'All computations were done on CPU on a personal laptop computer,' but does not provide specific details such as the CPU model, memory, or other hardware specifications.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an empirical experimental setup with specific hyperparameters, training configurations, or system-level settings.