Tianlong Chen, Zhangyang Wang, Xuxi Chen, Sijia Liu, Yanzhi Wang, Xiaohan Chen, Xiaolong Ma, Minghai Qin, Geng Yuan, Xuan Shen, Ning Liu
We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| boone891214/sanity-check-LTH | canonical | 1 of 1 |
| copy not recorded | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| accuracy | Ran | this paper's copy was not recorded; identical code first harvested from facebookresearch/barlowtwins pointer only · get_code("b0f936d4d6ae3b8c") |
| mixup_data | Ran | boone891214/sanity-check-LTH/cifar/main_prune_train.py pointer only (licence: NONE) · get_code("fd81207449c239dd") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
There have been long-standing controversies and inconsistencies over the experiment setup and criteria for identifying the "winning ticket" in literature. To reconcile such, we revisit the definition of lottery ticket hypothesis, with comprehensive and more rigorous conditions. Under our new definition, we show concrete evidence to clarify whether the winning ticket exists across the major DNN architectures and/or applications. Through extensive experiments, we perform quantitative analysis on the correlations between winning tickets and various experimental factors, and empirically study the patterns of our observations. We find that the key training hyperparameters, such as learning rate and training epochs, as well as the architecture characteristics such as capacities and residual connections, are all highly correlated with whether and when the winning tickets can be identified. Based on our analysis, we summarize a guideline for parameter settings in regards of specific architecture characteristics, which we hope to catalyze the research progress on the topic of lottery ticket hypothesis. Our codes are publicly available at: https://github.com/boone891214/sanity-check-LTH.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2107.00166")
get_code_for_paper("2107.00166")
have("2107.00166")
Connect an agent — have() is free.