Heteroscedastic Sequences: Beyond Gaussianity

Authors: Oren Anava, Shie Mannor

ICML 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The theoretical results are corroborated by an empirical study.
Researcher Affiliation Academia Oren Anava OANAVA@TX.TECHNION.AC.IL Technion, Haifa, Israel Shie Mannor SHIE@EE.TECHNION.AC.IL Technion, Haifa, Israel
Pseudocode Yes Algorithm 1 LAZY OGD (on the ℓ2 unit ball)
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology.
Open Datasets No The paper describes generating synthetic data using the ARCH model (Equations (6) and (7)) with specified parameters and error distributions, but it does not provide access information (link, DOI, citation) to a pre-existing publicly available dataset.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, or citations to predefined splits) for training, validation, or testing. It describes an online, sequential evaluation up to 1000 rounds.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes To test the robustness of our approach to different error distributions, we generate three time series using the ARCH model (Equations (6) and (7)) with u0 = (0, 0.55, 0.11) and v0 = (0.1, 0.25, 0.25), each differs only in its error distribution." and "if we choose ηSig = ηVar = 1 / sqrt(T)