Alternating Differentiation for Optimization Layers
Authors: Haixiang Sun, Ye Shi, Jingya Wang, Hoang Duong Tuan, H. Vincent Poor, Dacheng Tao
ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | A series of comprehensive experiments validate the superiority of Alt-Diff. (...) 5 EXPERIMENTAL RESULTS In this section, we evaluate Alt-Diff over a series of experiments to demonstrate its performance in terms of computational speed as well as accuracy. |
| Researcher Affiliation | Collaboration | Shanghai Tech University1, University of Technology Sydney2, Princeton University3, JD Explore Academy4 |
| Pseudocode | Yes | Algorithm 1 Alt-Diff |
| Open Source Code | Yes | Our source code for these experiments is available at https://github.com/HxSun08/Alt-Diff. |
| Open Datasets | Yes | We used two convolutional layers followed by Re LU activation functions and max pooling for feature extraction. (...) for image classification task on MNIST dataset. |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, and test sets. It mentions using the MNIST dataset and training a neural network but lacks details on data partitioning. |
| Hardware Specification | Yes | All the experiments were implemented on a Core Intel(R) i7-10700 CPU @ 2.90GHz with 16 GB of memory. |
| Software Dependencies | No | The paper mentions 'implemented using Py Torch with Adam optimizer' and 'under the Jax framework' but does not specify version numbers for these software components or any other libraries. |
| Experiment Setup | Yes | The batch size is set as 64 and the learning rate is set as 10-3. We ran 30 epoches and provided the running time and test accuracy in Tabel 7. |