Efficient Lottery Ticket Finding: Less Data is More
Authors: Zhenyu Zhang, Xuxi Chen, Tianlong Chen, Zhangyang Wang
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments validate our proposal across diverse datasets and network architectures. Specifically, on CIFAR-10, CIFAR-100, and Tiny Image Net, we locate effective Pr AC sets at 35.32% 78.19% of their training set sizes. |
| Researcher Affiliation | Collaboration | 1University of Science and Technology of China 2University of Texas at Austin. |
| Pseudocode | Yes | Algorithm 1 Data and Model Sparsity Co-Design |
| Open Source Code | Yes | Our implementations are available at: https://github. com/VITA-Group/Pr AC-LTH |
| Open Datasets | Yes | Our experiments use two popular architectures, Res Net (He et al., 2016) and VGG (Simonyan & Zisserman, 2014), on three representative datasets, i.e., CIFAR-10 (Krizhevsky et al., 2009), CIFAR-100 (Krizhevsky et al., 2009) and Tiny Image Net (Wu et al., 2017). |
| Dataset Splits | No | The paper mentions training and testing but does not explicitly state the use of a validation set or provide details on its split from the data. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for software libraries or dependencies used in the experiments. |
| Experiment Setup | Yes | General Setup. We summarize the key setups and hyperparameters of our implementation in Table 1, and refer readers to Appendix A1 for more details. Specifically, we train networks for 182 epochs with a multi-step learning rate schedule, which decays the learning rate to its one-tenth at epoch 91 and 136, respectively. Table 1 also provides details on Batch Size, Learning Rate, and Warmup settings for different networks and datasets. |