Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space
Authors: Shuo Yang, Yanyao Shen, Sujay Sanghavi
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We also demonstrate its value via synthetic experiments. Moreover, we numerically show that Int HT can be extended to higher-order regression problems, and also theoretically analyze an SVRG variant of Int HT. ... 5 Synthetic Experiments To examine the sub-quadratic time and space complexity, we design three tasks to answer the following three questions: |
| Researcher Affiliation | Academia | Shuo Yang Department of Computer Science University of Texas at Austin Austin, TX 78712 yangshuo_ut@utexas.edu Yanyao Shen ECE Department University of Texas at Austin Austin, TX 78712 shenyanyao@utexas.edu Sujay Sanghavi ECE Department University of Texas at Austin Austin, TX 78712 sanghavi@mail.utexas.edu |
| Pseudocode | Yes | Algorithm 1 INTERACTION HARD THRESHOLDING (INTHT) ... Algorithm 2 APPROXIMATED TOP ELEMENTS EXTRACTION (ATEE) |
| Open Source Code | No | The paper does not provide any links to open-source code or state that the code for their method is publicly available. |
| Open Datasets | No | The paper states: "We generate feature vectors xi, whose coordinates follow i.i.d. uniform distribution on [−1, 1]. ... The output yis, are generated following x⊤i Θ xi." This indicates the use of synthetically generated data, not a publicly available dataset with concrete access information. |
| Dataset Splits | No | The paper uses synthetically generated data and mentions experiments are "averaged over 3 independent runs" or "averaged over 5 independent runs," but it does not specify explicit training, validation, or test dataset splits in terms of percentages or sample counts. |
| Hardware Specification | No | The paper does not mention any specific hardware specifications (e.g., GPU models, CPU types, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not specify any software dependencies, libraries, or their version numbers used for the implementation or experiments. |
| Experiment Setup | Yes | Experimental setting ... by default, we set p = 200, d = 3, K = 20, k = 3K, η = 0.2. Support recovery results with different b-K combinations are averaged over 3 independent runs, results for m-p combinations are averaged over 5 independent runs. All experiments are terminated after 150 iterations. |