Regret in Online Recommendation Systems
Authors: Kaito Ariu, Narae Ryu, Se-Young Yun, Alexandre Proutiere
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | This paper proposes a theoretical analysis of recommendation systems in an online setting, where items are sequentially recommended to users over time. We investigate various structural assumptions on these probabilities: we derive for each structure regret lower bounds, and devise algorithms achieving these limits. We illustrate the performance of our algorithms through experiments presented in the appendix. |
| Researcher Affiliation | Academia | Kaito Ariu KTH Stockholm, Sweden ariu@kth.se Narae Ryu KAIST Daejeon, South Korea nrryu@kaist.ac.kr Se-Young Yun KAIST Daejeon, South Korea yunseyoung@kaist.ac.kr Alexandre Proutière KTH Stockholm, Sweden alepro@kth.se |
| Pseudocode | Yes | Due to space constraints, we present the pseudo-codes of our algorithms, all proofs, numerical experiments, as well as some insightful discussions in the appendix. |
| Open Source Code | No | No explicit statement or link indicating the public availability of the source code for the described methodology was found. |
| Open Datasets | No | The paper mentions "numerical experiments presented in the appendix" but does not specify any publicly available datasets or provide access information for them in the main text. |
| Dataset Splits | No | No specific information about dataset splits (e.g., training, validation, test percentages or counts) was found in the main text. |
| Hardware Specification | No | No specific hardware (e.g., GPU models, CPU types, or cloud resources) used for running experiments was mentioned. |
| Software Dependencies | No | No specific software names with version numbers were mentioned as dependencies for the experiments or implementation. |
| Experiment Setup | No | The paper describes algorithm phases and some parameters for item selection but does not provide specific experimental setup details such as hyperparameters (learning rates, batch sizes, epochs) or optimizer settings. |