Learning-Augmented Online Algorithm for Two-Level Ski-Rental Problem
Authors: Keyuan Zhang, Zhongdong Liu, Nakjung Choi, Bo Ji
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we conduct numerical experiments on both synthetic and real-world trace data to corroborate the effectiveness of our approach. |
| Researcher Affiliation | Collaboration | Keyuan Zhang1, Zhongdong Liu1, Nakjung Choi2, Bo Ji1 1Virginia Tech, Blacksburg, VA, USA 2Nokia Bell Labs, Murray Hill, NJ, USA keyuanz@vt.edu, zhongdong@vt.edu, nakjung.choi@nokia-bell-labs.com, boji@vt.edu |
| Pseudocode | Yes | Algorithm 1: Robust Deterministic Two-level Skirental (RDTSR) Algorithm |
| Open Source Code | Yes | Source code: https://github.com/nauyek/LADTSR. |
| Open Datasets | Yes | We use the traces of Virtual Machine (VM) workloads from Microsoft Azure (Cortez et al. 2017). |
| Dataset Splits | No | The paper mentions training and testing data but does not provide specific percentages or counts for a complete training/test/validation split, nor does it specify a cross-validation setup. |
| Hardware Specification | Yes | All the experiments are implemented in Python and are conducted on a laptop with a 12th Gen Intel(R) i5-12500H processor and 16GB memory. |
| Software Dependencies | No | The paper mentions 'Python' and 'TensorFlow' but does not specify their version numbers or other library versions needed for replication. |
| Experiment Setup | Yes | The network has two LSTM layers followed by one fully connected layer. The hidden states of the two LSTM layers are both 10, 256, and 10 for the Synthetic, Azure, and App Usage datasets, respectively. We use the mean absolute error as the loss function and employ the Adam optimizer to train the weights. |