Expectation Propagation for t-Exponential Family Using q-Algebra
Authors: Futoshi Futami, Issei Sato, Masashi Sugiyama
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We finally apply the proposed EP algorithm to the Bayes point machine and Student-t process classification, and demonstrate their performance numerically. [...] In this section, we numerically illustrate the behavior of our proposed EP applied to BPM and Studentt process classification. |
| Researcher Affiliation | Academia | Futoshi Futami The University of Tokyo, RIKEN futami@ms.k.u-tokyo.ac.jp Issei Sato The University of Tokyo, RIKEN sato@k.u-tokyo.ac.jp Masashi Sugiyama RIKEN, The University of Tokyo sugi@k.u-tokyo.ac.jp |
| Pseudocode | No | The paper describes algorithms and derivations textually and mathematically, but it does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any statements or links indicating that the authors' source code for the described methodology is publicly available. |
| Open Datasets | Yes | We compared the performance of Gaussian process and Student-t process classification on the UCI datasets. [...] Dataset Outliers GPC STC Pima [...] Ionosphere [...] Thyroid [...] Sonar |
| Dataset Splits | No | The paper describes generating a toy dataset and using UCI datasets, but it does not provide specific details on training, validation, or test splits (e.g., percentages, sample counts, or predefined splits). |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers (e.g., libraries, frameworks, solvers). |
| Experiment Setup | Yes | In the experiment, we used v = 10 for Student-t processes. We furthermore used the following kernel: k(xi, xj) = θ0 exp{−P d=1 θd−1(xd i − xd j)2} + θ2 + θ3δi,j, where xd i is the dth element of xi, and θ0, θ1, θ2, θ3 are hyperparameters to be optimized. The detailed explanation about experimental settings are given in Appendix F. |