Asymptotics for Sketching in Least Squares Regression
Authors: Edgar Dobriban, Sifan Liu
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our theoretical results are verified on both real and synthetic data. We verify these results in extensive simulations and on two empirical datasets. We report some simulations to verify our results. In Figure 1, we take n = 2000, and p = 100 or 800, respectively. The simulation results of VE and the error bar are the mean and one standard deviation over 10 repetitions. We test our results on the Million Song Year Prediction Dataset (MSD) (Bertin-Mahieux et al., 2011) (n = 515344, p = 90) and the New York flights dataset (Wickham, 2018) (n = 60449, p = 21). |
| Researcher Affiliation | Academia | Edgar Dobriban Department of Statistics University of Pennsylvania Philadelphia, PA 19104 dobriban@wharton.upenn.edu Sifan Liu Department of Statistics Stanford University Stanford, CA 94305 sfliu@stanford.edu |
| Pseudocode | No | The paper describes algorithms and methods but does not provide any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or link for open-source code related to the described methodology. It mentions 'A version of our manuscript is available on arxiv at https://arxiv.org/abs/1810.06089', which is a paper preprint, not code. |
| Open Datasets | Yes | We test our results on the Million Song Year Prediction Dataset (MSD) (Bertin-Mahieux et al., 2011) (n = 515344, p = 90) and the New York flights dataset (Wickham, 2018) (n = 60449, p = 21). |
| Dataset Splits | No | The paper does not explicitly provide details about training/validation/test splits, only mentioning the total number of samples (n) and features (p) for the datasets used. It discusses 'training and test data X and xt' but without specifying the split percentages or sizes. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for the experiments, such as GPU models, CPU types, or memory specifications. |
| Software Dependencies | No | The paper does not list any specific software dependencies with version numbers. |
| Experiment Setup | No | The paper describes how X is generated ('Each row of X is generated iid from N(0, Ip)') and states sample sizes (n=2000, p=100 or 800) for simulations, but it does not specify general experimental setup details like learning rates, batch sizes, optimizers, or other hyperparameters. It mentions 'The columns are standardized to have zero mean and unit standard deviation' for empirical data, but lacks more comprehensive setup details. |