Multivariate Probability Calibration with Isotonic Bernstein Polynomials
Authors: Yongqiao Wang, Xudong Liu
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our empirical study shows that the proposed method achieves better calibrating performance than benchmark methods. Experiments are performed on five large data from [Dua and Graff, 2017] with size larger than 40,000: Adult, Census, Covertype, Dota2 and SUSY. |
| Researcher Affiliation | Academia | Yongqiao Wang1 and Xudong Liu2 1College of Finance, Zhejiang Gongshang University, China 2School of Computing, University of North Florida, USA |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described in this paper. It mentions CVX [Grant and Boyd, 2014] as a tool used, but not the authors' own implementation. |
| Open Datasets | Yes | Experiments are performed on five large data from [Dua and Graff, 2017] with size larger than 40,000: Adult, Census, Covertype, Dota2 and SUSY. |
| Dataset Splits | Yes | We randomly draw 200 samples for training two classifiers and 400 samples for training the calibrating model. All other samples are used for testing calibration models. In each training step, we use 5-fold cross-validation to determine hyperparameters. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments. It only mentions "CPU time" for running time analysis. |
| Software Dependencies | No | The paper mentions "CVX [Grant and Boyd, 2014]" but does not specify a version number within the body of the text regarding its usage. The reference itself indicates version 2.1, but this is not explicitly stated in the experimental setup section for the version used by the authors. |
| Experiment Setup | Yes | The hyperparameters are arbitrarily chosen: λ = 10 5 in MR-MIC, and K1 = K2 = 5 in the proposed method. |