Online Forecasting of Total-Variation-bounded Sequences

Authors: Dheeraj Baby, Yu-Xiang Wang

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To empirically validate our results, we conducted a number of numerical simulations that compares the regret of ARROWS, (Restarting) OGD and MA. Figure 2 shows the results on a function with heterogeneous smoothness (see the exact details and more experiments in Appendix B).
Researcher Affiliation Academia Dheeraj Baby Department of Computer Science UC Santa Barbara dheeraj@ucsb.edu Yu-Xiang Wang Department of Computer Science UC Santa Barbara yuxiangw@cs.ucsb.edu
Pseudocode Yes ARROWS: inputs observed y values, time horizon n, std deviation σ, δ (0, 1], a hyperparameter β > 24
Open Source Code No The paper does not provide any explicit statement about making the source code available or include a link to a code repository.
Open Datasets No The paper discusses simulations on "sequences" and "functions" with "heterogeneous smoothness" but does not refer to any named public datasets or provide links/citations for data used in simulations.
Dataset Splits No The paper does not specify any dataset splits (e.g., percentages or sample counts for training, validation, or testing) for its simulations.
Hardware Specification No The paper does not specify any hardware used for running the simulations or experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers used for the experiments or implementation.
Experiment Setup Yes ARROWS: inputs observed y values, time horizon n, std deviation σ, δ (0, 1], a hyperparameter β > 24. The hyperparameters selected according to their theoretical optimal choice for the TV class (See Theorem 11, 12 for OGD and MA in Appendix C).