Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks
Authors: Shuoguang Yang, Xuezhou Zhang, Mengdi Wang
NeurIPS 2022 | Venue PDF | LLM Run Details | Input Tokens: 19,113 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,916 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We test our algorithm on the examples of hyperparameter tuning and decentralized reinforcement learning. Simulated experiments confirmed that our algorithm achieves the state-of-the-art training efficiency and test accuracy. |
| Researcher Affiliation | Academia | Shuoguang Yang IEDA, HKUST EMAIL Xuezhou Zhang Princeton University EMAIL Mengdi Wang Princeton University EMAIL |
| Pseudocode | Yes | Algorithm 1 Gossip-Based Decentralized Stochastic Bilevel Optimization |
| Open Source Code | No | We will provide the code via github in the camera-ready version stage. |
| Open Datasets | Yes | Hyper-parameter Optimization We consider federated hyper-parameter optimization (2) for a handwriting recognition problem over the Australia handwriting dataset (Chang and Lin, 2011) |
| Dataset Splits | No | Before testing Alg. 1, we first randomly split the dataset for training and validation, and then allocates both training and validation dataset over K agents. |
| Hardware Specification | No | We run the experiments on a single server desktop computer. |
| Software Dependencies | No | The paper does not specify any software names with version numbers. |
| Experiment Setup | Yes | We then run Algorithm 1 for T = 20000 iterations, with b = 200, t = 0.1 K/T, and βt = γt = 10 |