Efficient Contextual Bandits with Uninformed Feedback Graphs

Authors: Mengxiao Zhang, Yuheng Zhang, Haipeng Luo, Paul Mineiro

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also demonstrate the empirical effectiveness of our algorithm on a bidding application using both synthetic and real-world data.
Researcher Affiliation Collaboration 1University of Southern California 2University of Illinois Urbana-Champaign 3Microsoft Research.
Pseudocode Yes Algorithm 1 Square CB.UG
Open Source Code No The paper does not provide any concrete access information (e.g., specific repository link, explicit code release statement) for the source code of the methodology described.
Open Datasets Yes We also conduct experiments on a subset of 5000 samples of a real e Bay auction dataset used in Mohri & Medina (2016); see Appendix C for details... The real auction dataset we used in Section 5.2 is an e Bay auction dataset (available at https://cims.nyu.edu/ munoz/data/)
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, and testing. It discusses online learning but does not define traditional splits.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions general machine learning components like 'linear classification model' and 'two-layered fully connected neural network' but does not specify software names with version numbers (e.g., PyTorch 1.9, TensorFlow 2.x) to replicate the experiment.
Experiment Setup Yes For Square CB, we set the exploration parameter γ = c sqrt(KT) (based on what its theory suggests), where c is searched over {0.5, 1, 2}. For our Square CB.UG, we set γ = c sqrt(T), where c is also searched over {0.5, 1, 2}... For experiments on the real auction dataset, learning rate is searched over {0.005, 0.01, 0.05} for the loss oracle and over {0.01, 0.05} for the graph regression oracle. For experiments on the synthetic datasets, they are searched over {0.005, 0.01, 0.02} and {0.01, 0.05} respectively. The experiment on the real auction dataset is repeated with 8 different random seeds and the experiment on the synthetic datasets is repeated with 4 different random seeds.