CoNSoLe: Convex Neural Symbolic Learning

Authors: Haoran Li, Yang Weng, Hanghang Tong

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we demonstrate the superior performance of the CONSOLE framework over the state-of-the-art on a diverse set of datasets. 1 Introduction ...5 Experiments ...5.1 Settings ...5.2 Verification and 3-D Visualization of Convex Mechanisms ...5.3 Convexity Guarantees of CONSOLE to Learn Correct Equations ...5.4 Ablation Study: Exploration and Convex Search are Essential ...5.5 CONSOLE is Robust with Changing Noise Levels and Data Volume
Researcher Affiliation Academia Haoran Li Yang Weng Arizona State University Tempe, AZ, 85287 {lhaoran, yang.weng}@asu.edu Hanghang Tong University of Illinois Urbana-Champaign Champaign, IL, 61820 htong@illinois.edu
Pseudocode Yes The overview of our framework is in Appendix A.1, Algorithm 1. The specific algorithm is in Appendix A.2, Algorithm 2.
Open Source Code No The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper describes creating its own synthetic datasets (Syn1, Syn2) and generating data through simulations using MATPOWER [39] for the Pow dataset and MATLAB for the Mas dataset. No concrete access information for publicly available datasets is provided.
Dataset Splits No The paper describes training and testing data splits (e.g., '2,000 samples for training... another 2,000 samples... for test'; 'first 8,760 points are used for training while the remaining samples are used for testing'), but does not explicitly mention a separate validation dataset split.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions using 'MATPOWER' and 'MATLAB' for simulations, but does not provide specific version numbers for these or any other software dependencies required to replicate the experiments.
Experiment Setup Yes Finally, the hyper-parameter settings can be seen in Appendix A.7.