Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms

Authors: Yingying Li, Na Li

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

Reproducibility Variable Result LLM Response
Research Type Experimental Lastly, we numerically test the performance of RHIG on quadrotor tracking problems.
Researcher Affiliation Academia Yingying Li SEAS Harvard University Cambridge, MA, USA. 02138 yingyingli@g.harvard.edu Na Li SEAS Harvard University Cambridge, MA, USA. 02138 nali@seas.harvard.edu
Pseudocode Yes Algorithm 2: Receding Horizon Inexact Gradient (RHIG)
Open Source Code No The paper does not provide an unambiguous statement of releasing open-source code for the described methodology, nor does it include a direct link to a code repository.
Open Datasets No The paper describes generating data based on models (e.g., 'quadrotor tracking of a vertically moving target [37]', 'target θt follows: θt = yt + qt, where yt = γyt 1 + et is an autoregressive process with noise et [38]') but does not provide concrete access information (link, DOI, repository, or specific dataset name with access) for a publicly available dataset.
Dataset Splits No The paper describes numerical experiments but does not provide specific details on training, validation, or test dataset splits (e.g., percentages, sample counts, or cross-validation setup).
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment.
Experiment Setup No The paper discusses model parameters for the quadrotor tracking problem (e.g., 'min PT t=1 1 2(α(xt θt)2 + β(xt xt 1)2)', 'γ = 0.3 and γ = 0.7') but does not provide specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size) or training configurations for the RHIG algorithm.