Launch and Iterate: Reducing Prediction Churn
Authors: Mahdi Milani Fard, Quentin Cormier, Kevin Canini, Maya Gupta
NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on benchmark datasets for different classification algorithms demonstrate the method and the resulting reduction in churn. |
| Researcher Affiliation | Collaboration | Q. Cormier ENS Lyon 15 parvis René Descartes Lyon, France quentin.cormier@ens-lyon.fr M. Milani Fard, K. Canini, M. R. Gupta Google Inc. 1600 Amphitheatre Parkway Mountain View, CA 94043 {mmilanifard,canini,mayagupta}@google.com |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any information about open-source code being made available for the described methodology. |
| Open Datasets | Yes | This section demonstrates the churn reduction effect of the RCP operator for three UCI benchmark datasets (see Table 2) with three regression algorithms: ridge regression, random forest regression, and support vector machine regression with RBF kernel, all implemented in Scikit-Learn [12]. [...] Nomao [13] News Popularity [14] Twitter Buzz [15] |
| Dataset Splits | Yes | We randomly split each dataset into three fixed parts: a training set, a validation set on which we optimized the hyper-parameters for all algorithms, and a testing set. [...] Table 2: Validation set 1000 samples (for each dataset) |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions 'all implemented in Scikit-Learn [12]' but does not specify a version number for Scikit-Learn or any other software dependencies. |
| Experiment Setup | Yes | We used fixed values of α = 0.5 and ϵ = 0.5 for all the experiments in Table 3 [...] The dataset perturbation sub-samples 80% of the examples in TA and randomly drops 3-7 features. We run 40 independent chains to measure the variability, and report the average outcome and standard deviation. [...] See the supplementary material for more experimental details. |