A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization
Authors: Risheng Liu, Xuan Liu, Xiaoming Yuan, Shangzhi Zeng, Jin Zhang
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments demonstrate the efficiency of the proposed BVFIM on non-convex bi-level problems. In this section, we present numerical simulations with the proposed methods and demonstrate application in hyperparameter optimization for non-convex LL problems. |
| Researcher Affiliation | Academia | 1DUT-RU International School of Information Science and Engineering, Dalian University of Technology. 2Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province. 3Pazhou Lab, Guangzhou. 4Department of Mathematics, The University of Hong Kong. 5Department of Mathematics, Southern University of Science and Technology. 6National Center for Applied Mathematics Shenzhen. |
| Pseudocode | Yes | Algorithm 1 Our Solution Strategy for Eq. (13) |
| Open Source Code | No | The paper does not contain any statement about releasing source code for the methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | Our experiment is based on MNIST, Fashion MNIST (Xiao et al., 2017) and CIFAR10 datasets. |
| Dataset Splits | Yes | For each dataset, we randomly select 5000 samples as the training set Dtr, 5000 samples as the validation set Dval, and 10000 samples as the test set Dtest. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU/CPU models, processor types, or memory used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment. |
| Experiment Setup | No | The paper mentions 'The adaptive (µ, θ, τ) means to follow the default setting which can be found in Supplementary Materials' but does not provide specific hyperparameter values or detailed training configurations within the main text. |