First-Order Convex Fitting and Its Application to Economics and Optimization
Authors: Quinlan Dawkins, Minbiao Han, Haifeng Xu6480-6487
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we demonstrate another potential application of FCF, i.e., accelerating convex optimization, by presenting a set of thorough empirical studies. Our promising empirical results give rise to an intriguing future research direction of rigorously understanding how FCF can accelerate convex optimization. We note that this is outside of the scope of the present paper which aims at studying the FCF problem itself and demonstrating its potential usefulness. ... In this section, we present the experiment results for the larger dateset covtype in Table 2. |
| Researcher Affiliation | Academia | Quinlan Dawkins, Minbiao Han, Haifeng Xu Department of Computer Science, University of Virginia {qed4wg, mh2ye, hx4ad}@virginia.edu |
| Pseudocode | Yes | Algorithm 1: Construction of the FCF Convex Function |
| Open Source Code | No | No explicit statement about the release of open-source code for the paper's methodology or a link to a code repository was found. |
| Open Datasets | Yes | We use two classical datasets: (1) covtype7 from UCI which has N = 581, 012 data points and d = 54 features dimensions; (2) ijcnn18 which has N = 49, 990 data points and d = 22 features dimensions. (7) https://archive.ics.uci.edu/ml/datasets/covertype (8) http://www.geocities.ws/ijcnn/nnc_ijcnn01.pdf |
| Dataset Splits | No | The paper mentions using 'covtype' and 'ijcnn1' datasets but does not explicitly provide details about training, validation, or test dataset splits (e.g., percentages or sample counts). |
| Hardware Specification | Yes | All the algorithms are coded in Python and the experiments were run on a single core of a 2.20GHz Intel Xeon Silver 4210 CPU using 256 GB of RAM. |
| Software Dependencies | No | The paper states 'All the algorithms are coded in Python' but does not provide specific version numbers for Python or any other software libraries or dependencies used. |
| Experiment Setup | Yes | Our experiment uses the standard l2 norm as regularization. ... Each set of experiments has three regularization regimes, high (λ = 0.1), medium (λ = 0.01), and low (λ = 0.001). ... parameter: resolution ϵ = e 4, integer k Function SMCF(): |