On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

Authors: Weitong Zhang, Jiafan He, Zhiyuan Fan, Quanquan Gu

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on both synthetic and real-world datasets corroborate our theoretical results.
Researcher Affiliation Academia 1Department of Computer Science, University of California, Los Angeles, California, USA 2IIIS, Tsinghua University, Beijing, China. Correspondence to: Quanquan Gu <qgu@cs.ucla.edu>.
Pseudocode Yes Algorithm 1 Data Selection OFUL (DS-OFUL) Algorithm 2 Sup Lin UCB
Open Source Code No The paper does not contain an explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes To demonstrate that the proposed algorithm can be easily applied to modern machine learning tasks, we carried out experiments on the Asirra dataset (Elson et al., 2007).
Dataset Splits No The paper discusses the total number of rounds (K) for experiments but does not explicitly provide details on train/validation/test dataset splits, percentages, or methodology for reproducibility.
Hardware Specification Yes The experiment on synthetic dataset is conducted on Google Colab with a 2-core Intel Xeon CPU @ 2.20GHz. The experiment on the real-world Asirra dataset (Elson et al., 2007) is conducted on an AWS p2xlarge instance.
Software Dependencies No The paper mentions models like 'Res Net-18' but does not specify software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow, or specific library versions).
Experiment Setup Yes We do a grid search for β = {1, 3, 10}, λ = {1, 3, 10} and report the cumulative regret of Algorithm 1 with different parameter Γ = {0, 0.02, 0.05, 0.08, 0.18} over 8 independent trials with total rounds K = 10000. For hyper-parameter tuning, we select β = {0.1, 0.3, 1} and λ = {1, 3, 10} by doing a grid search and repeat the experiments for 8 times over 1M rounds for each parameter configuration.