Concentration Tail-Bound Analysis of Coevolutionary and Bandit Learning Algorithms
Authors: Per Kristian Lehre, Shishen Lin
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiments with the RLS-PD for the maximin BILINEAR problem. and Figure 1 displays the density plot for the runtime distribution of RLS-PD on BILINEAR. and We conduct experiments with the RWAB Algorithm for the 2-armed non-stationary bandit problem. |
| Researcher Affiliation | Academia | Per Kristian Lehre , Shishen Lin University of Birmingham, Birmingham, United Kingdom {p.k.lehre, sxl1242}@cs.bham.ac.uk |
| Pseudocode | Yes | We defer pseudo-codes of algorithms and tables in the appendix. |
| Open Source Code | No | The paper does not contain an explicit statement about the release of source code for the methodology described, nor does it provide a link to a code repository. |
| Open Datasets | No | The experiments use problem setups (BILINEAR function parameters and bandit problem configurations) which are defined within the paper, rather than publicly available datasets with explicit access information. |
| Dataset Splits | No | The paper describes running simulations based on defined problem configurations but does not mention specific training, validation, or test dataset splits or cross-validation setups. |
| Hardware Specification | No | The paper mentions computations were performed using 'the University of Birmingham s Blue BEAR high performance computing (HPC) service,' which is a general service description and does not provide specific hardware details like GPU/CPU models, processors, or memory. |
| Software Dependencies | No | The paper does not provide specific software dependency names with version numbers for replication (e.g., Python 3.x, PyTorch x.x, or specific solver versions). |
| Experiment Setup | Yes | The problem setup is (α, β) = (0.5, 0.5), (0.3, 0.3), (0.3, 0.7), (0.7, 0.3), (0.7, 0.7). We set the mutation rate χ = 1 and problem size n = 1000. We run 1000 independent simulations for each configuration. For each run, we initialise the search point uniformly at random. and The environment is set up as two Bernoulli bandits with means µ1 = 0.2, µ2 = 0.8 and the number of changes L = 5, 10, 20, 40, 80, 100. The changes are set up uniformly at random along the time horizon T = 1000. 1000 independent simulations are run for each configuration. |