Uncertainty Regularized Evidential Regression

Authors: Kai Ye, Tiejin Chen, Hua Wei, Liang Zhan

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our extensive experiments substantiate our theoretical findings and demonstrate the effectiveness of the proposed solution.
Researcher Affiliation Academia 1University of Pittsburgh, Pittsburgh, PA, 15260, USA 2Arizona State University, Tempe, AZ, 85281, USA
Pseudocode No The paper describes its methods mathematically and textually but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes 1Code is at https://github.com/FlynnYe/UR-ERN
Open Datasets Yes Following (Amini et al. 2020), we train models on y = x3 + ϵ, where ϵ N(0, 3). We conduct training over the interval x [ 4, 4], and perform testing over x [ 6, 4) (4, 6]." and "We choose the NYU Depth v2 dataset (Silberman et al. 2012) for experiments.
Dataset Splits No The paper mentions training and testing intervals for the cubic regression dataset, but it does not explicitly provide training/validation/test dataset splits (e.g., percentages, sample counts, or cross-validation details) for reproducibility, nor does it specify how validation data was used.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., 'Python 3.8', 'PyTorch 1.9') that would be necessary to replicate the experiment environment.
Experiment Setup Yes For experiments within HUA, we initialize the model within HUA by setting bias in the activation layer." and "Please refer to Appendix B for details about experimental setups and experiments about the sensitivity of hyperparameters.