Online Stochastic Optimization under Correlated Bandit Feedback

Authors: Mohammad Gheshlaghi azar, Alessandro Lazaric, Emma Brunskill

ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental While our primary contribution is the definition of HCT and its technical analysis, we also give preliminary simulation results to demonstrate some of its properties. and 6. Numerical Results
Researcher Affiliation Academia Mohammad Gheshlaghi Azar MOHAMMAD.AZAR@NORTHWESTERN.EDU Rehabilitation Institute of Chicago, Northwestern University, Alessandro Lazaric ALESSANDRO.LAZARIC@INRIA.FR Team Seque L, INRIA Nord Europe, Emma Brunskill EBRUN@CS.CMU.EDU School of Computer Science, CMU
Pseudocode Yes Algorithm 1 The HCT algorithm. and Algorithm 2 The Opt Traverse function. and Algorithm 3 The Update B function.
Open Source Code No The paper does not provide any explicit statement or link regarding the availability of open-source code for the described methodology.
Open Datasets No We focus on minimizing the regret across repeated noisy evaluations of the garland function f(x) = x(1 x)(4 | sin(60x)|) relative to repeatedly selecting its global optima. We discuss some properties of the garland function in Sect. C of the supplement where the function is illustrated in Fig. 3. (The garland function is a synthetic function used for simulation, not a publicly available dataset.)
Dataset Splits No The paper does not provide specific dataset split information (e.g., percentages, sample counts, or citations to predefined splits) needed to reproduce data partitioning for training, validation, or testing.
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 No For all the algorithms compared in the following, parameters are optimized to maximize their performance. (This statement is too general and does not specify concrete hyperparameter values or detailed configurations.)